[HN Gopher] Small models also found the vulnerabilities that Myt...
       ___________________________________________________________________
        
       Small models also found the vulnerabilities that Mythos found
        
       Author : dominicq
       Score  : 1225 points
       Date   : 2026-04-11 16:47 UTC (1 days ago)
        
 (HTM) web link (aisle.com)
 (TXT) w3m dump (aisle.com)
        
       | epistasis wrote:
       | > We took the specific vulnerabilities Anthropic showcases in
       | their announcement, isolated the relevant code, and ran them
       | through small, cheap, open-weights models. Those models recovered
       | much of the same analysis. Eight out of eight models detected
       | Mythos's flagship FreeBSD exploit, including one with only 3.6
       | billion active parameters costing $0.11 per million tokens.
       | 
       | Impressive, and very valuable work, but isolating the relevant
       | code changes the situation so much that I'm not sure it's much of
       | the same use case.
       | 
       | Being able to dump an entire code base and have the model scan it
       | is they type of situation where it opens up vulnerability scans
       | to an entirely larger class of people.
        
         | odie5533 wrote:
         | Isn't the difference just harness then? I can write a harness
         | that chunks code into individual functions or groups of
         | functions and then feed it into a vulnerability analysis agent.
        
           | jcims wrote:
           | It's probably not the 'only' difference, because clearly the
           | models are advancing in capability, but it's likely way more
           | important than generally given credit for.
        
         | elicash wrote:
         | This is from the first of the caveats that they list:
         | 
         | > Scoped context: Our tests gave models the vulnerable function
         | directly, often with contextual hints (e.g., "consider
         | wraparound behavior"). A real autonomous discovery pipeline
         | starts from a full codebase with no hints. The models'
         | performance here is an upper bound on what they'd achieve in a
         | fully autonomous scan. That said, a well-designed scaffold
         | naturally produces this kind of scoped context through its
         | targeting and iterative prompting stages, which is exactly what
         | both AISLE's and Anthropic's systems do.
         | 
         | That's why their point is what the subheadline says, that the
         | moat is the system, not the model.
         | 
         | Everybody so far here seems to be misunderstanding the point
         | they are making.
        
           | wat10000 wrote:
           | If that's the case, why didn't they do it that way?
        
             | e12e wrote:
             | Tunnel vision? If your model can handle big context, why
             | divide into lesser problems to conquer - even if such
             | splitting might be quite trivial and obvious?
             | 
             | It's the difference of "achieve the goal", and "achieve the
             | goal in this one particular way" (leverage large context).
        
               | wat10000 wrote:
               | I meant, if the claim here is that small models can
               | accomplish the same things with good scaffolding, why
               | didn't they demonstrate finding those problem with good
               | scaffolding rather than directly pointing them at the
               | problem?
        
               | mattmanser wrote:
               | They don't have to.
               | 
               | Lot of people in this thread don't seem to be getting
               | that.
               | 
               | If another model can find the vulnerability if you point
               | it at the right place, it would also find the
               | vulnerability if you scanned each place individually.
               | 
               | People are talking about false positives, but that also
               | doesn't matter. Again, they're not thinking it through.
               | 
               | False positives don't matter, as you can just
               | automatically try and exploit the "exploit" and if it
               | doesn't work, it's a false positive.
               | 
               | Worse, we have no idea how Mythos actually worked, it
               | could have done the process I've outlined above, "found"
               | 1,000s of false positives and just got rid of them by
               | checking them.
               | 
               | The fundamental point is it doesn't matter how the cheap
               | models identified the exploit, it's that they can
               | identify the exploit.
               | 
               | When it turns out the harness is just acting as a
               | glorified for-each brute force, it's not the model being
               | intelligent, it's simply the harness covering more
               | ground. It's millions of monkeys bashing type-writers,
               | not Shakespeare at one.
        
               | LordDragonfang wrote:
               | > If another model can find the vulnerability if you
               | point it at the right place, it would also find the
               | vulnerability if you scanned each place individually.
               | 
               | They didn't just point it at the right place, they
               | pointed it at the right place and _gave it hints_. That
               | 's a huge difference, even for humans.
        
               | wat10000 wrote:
               | It's strange to see this constant "I could do that too, I
               | just don't want to" response.
               | 
               | Finding an important decades-old vulnerability in OpenBSD
               | is extremely impressive. That's the sort of thing anyone
               | would be proud to put on their resume. Small models are
               | available for anyone to use. Scaffolding isn't that hard
               | to build. So why didn't someone use this technique to
               | find this vulnerability and make some headlines before
               | Anthropic did? Either this technique with small models
               | doesn't actually work, or it does work but nobody's out
               | there trying it for some reason. I find the second
               | possibility a lot less plausible than the first.
        
               | cycomanic wrote:
               | From the article: >At AISLE, we've been running a
               | discovery and remediation system against live targets
               | since mid-2025: 15 CVEs in OpenSSL (including 12 out of
               | 12 in a single security release, with bugs dating back
               | 25+ years and a CVSS 9.8 Critical), 5 CVEs in curl, over
               | 180 externally validated CVEs across 30+ projects
               | spanning deep infrastructure, cryptography, middleware,
               | and the application layer.
               | 
               | They have been doing it (and likely others as well), but
               | they are not anthropic which a million dollar marketing
               | budget and a trillion dollar hype behind it, so you just
               | didn't hear about it.
        
               | roywiggins wrote:
               | They could have linked their replication in this blog
               | post, which we did all see, if they have one.
        
               | mattmanser wrote:
               | Why are you EXTREMELY impressed? The level of hysteria
               | and lack of objective thought by pro-AI people on this
               | thread is extremely concerning.
               | 
               | Vulnerabilities are found every day. More will be found.
               | 
               | They claim they spent $20k finding one, probably more
               | like $20 million if you actually dug into it.
               | 
               | And if you took into account inference, more like $2
               | billion.
               | 
               | The reason why no-one's done it is because it's not worth
               | the money in tokens to do so.
        
           | anotheryou wrote:
           | huh, running it over each function in theory but testing just
           | the specific ones here makes sense, but that hint?!
        
             | elicash wrote:
             | I agree.
             | 
             | To clarify, I don't necessarily agree with the post or
             | their approach. I just thought folks were misreading it. I
             | also think it adds something useful to the conversation.
        
           | TacticalCoder wrote:
           | > That's why their point is what the subheadline says, that
           | the moat is the system, not the model.
           | 
           | Can you expand a bit more on this? What is the system then in
           | this case? And how was that model created? By AI? By humans?
        
             | SCHiM wrote:
             | You can imagine a pipeline that looks at individual source
             | files or functions. And first "extracts" what is going on.
             | You ask the model:
             | 
             | - "Is the code doing arithmetic in this file/function?" -
             | "Is the code allocating and freeing memory in this
             | file/function?" - "Is the code the code doing X/Y/Z? etc
             | etc"
             | 
             | For each question, you design the follow-up vulnerability
             | searchers.
             | 
             | For a function you see doing arithmetic, you ask:
             | 
             | - "Does this code look like integer overflow could take
             | place?",
             | 
             | For memory:
             | 
             | - "Do all the pointers end up being freed?" _or_ - "Do all
             | pointers only get freed once?"
             | 
             | I think that's the harness part in terms of generating the
             | "bug reports". From there on, you'll need a bunch of tools
             | for the model to interact with the code. I'd imagine you'll
             | want to build a harness/template for the file/code/function
             | to be loaded into, and executed under ASAN.
             | 
             | If you have an agent that thinks it found a bug: "Yes file
             | xyz looks like it could have integer overflow in function
             | abc at line 123, because...", you force another agent to
             | load it in the harness under ASAN and call it. If ASAN
             | reports a bug, great, you can move the bug to the next
             | stage, some sort of taint analysis or reach-ability
             | analysis.
             | 
             | So at this point you're running a pipeline to: 1) Extract
             | "what this code does" at the file, function or even line
             | level. 2) Put code you suspect of being vulnerable in a
             | harness to verify agent output. 3) Put code you confirmed
             | is vulnerable into a queue to perform taint analysis on, to
             | see if it can be reached by attackers.
             | 
             | Traditionally, I guess a fuzzer approached this from 3 ->
             | 2, and there was no "stage 1". Because LLMs "understand"
             | code, you can invert this system, and work if up from
             | "understanding", i.e. approach it from the other side. You
             | ask, given this code, is there a bug, and if so can we
             | reach it?, instead of asking: given this public interface
             | and a bunch of data we can stuff in it, does something
             | happen we consider exploitable?
        
               | ang_cire wrote:
               | That's funny, this is how I've been doing security
               | testing in my code for a while now, minus the 'taint
               | analysis'. Who knew I was ahead of the game. :P
               | 
               | In all seriousness though, it scares me that a lot of
               | security-focused people seemingly haven't learned how
               | LLMs work best for this stuff already.
               | 
               | You should always be breaking your code down into
               | testable chunks, with sets of directions about how to
               | chunk them and what to do with those chunks. Anyone just
               | vaguely gesturing at their entire repo going, "find the
               | security vulns" is not a serious dev/tester; we wouldn't
               | accept that approach in manual secure coding processes/
               | SSDLCs.
        
               | decidu0us9034 wrote:
               | In a large codebase there will still be bugs in how these
               | components interoperate with each other, bugs involving
               | complex chaining of api logic or a temporal element.
               | These are the kind of bugs fuzzers generally struggle at
               | finding. I would be a little freaked out if LLMs started
               | to get good at finding these. Everything I've seen so far
               | seems similar to fuzzer finds.
        
               | decidu0us9034 wrote:
               | I think there is already papers and presentations on
               | integrating these kind of iterative code
               | understanding/verificaiton loops in harnesses. There may
               | be some advantages over fuzzing alone. But I think the
               | cost-benefit analysis is a lot more mixed/complex than
               | anthropic would like people to believe. Sure you need
               | human engineers but it's not like insurmountably hard for
               | a non-expert to figure out
        
           | tehryanx wrote:
           | I get what you're saying, but I think this is still missing
           | something pretty critical.
           | 
           | The smaller models can recognize the bug when they're looking
           | right at it, that seems to be verified. And with AISLE's
           | approach you can iteratively feed the models one segment at a
           | time cheaply. But if a bug spans multiple segments, the small
           | model doesn't have the breadth of context to understand those
           | segments in composite.
           | 
           | The advantage of the larger model is that it can retain more
           | context and potentially find bugs that require more code
           | context than one segment at a time.
           | 
           | That said, the bugs showcased in the mythos paper all seemed
           | to be shallow bugs that start and end in a single input
           | segment, which is why AISLE was able to find them. But having
           | more context in the window theoretically puts less shallow
           | bugs within range for the model.
           | 
           | I think the point they are making, that the model doesn't
           | matter as much as the harness, stands for shallow bugs but
           | not for vulnerability discovery in general.
        
             | cyanydeez wrote:
             | OK, consider a for loop that goes through your repo, then
             | goes through each file, and then goes through each common
             | vulnerability...
             | 
             | Is Mythos some how more powerful than just a recursive
             | foreloop aka, "agentic" review. You can run `open code run
             | --command` with a tailored command for whatever
             | vulnerabilities you're looking for.
        
               | tehryanx wrote:
               | newer models have larger context windows, and more stable
               | reasoning across larger context windows.
               | 
               | If you point your model directly at the thing you want it
               | to assess, and it doesn't have to gather any additional
               | context you're not really testing those things at all.
               | 
               | Say you point kimi and opus at some code and give them an
               | agentic looping harness with code review tools. They're
               | going to start digging into the code gathering context by
               | mapping out references and following leads.
               | 
               | If the bug is really shallow, the model is going to get
               | everything it needs to find it right away, neither of
               | them will have any advantage.
               | 
               | If the bug is deeper, requires a lot more code context,
               | Opus is going to be able to hold onto a lot more
               | information, and it's going to be a lot better at
               | reasoning across all that information. That's a test that
               | would actually compare the models directly.
               | 
               | Mythos is just a bigger model with a larger context
               | window and, presumably, better prioritization and
               | stronger attention mechanisms.
        
               | cyanydeez wrote:
               | Harnesses are basically doing this better than just
               | adding more context. Every time, REGARDLESS OF MODEL
               | SIZE, you add context, you are increasing the odds the
               | model will get confused about any set of thoughts. So
               | context size is no longer some magic you just sprinkle on
               | these things and they suddenly dont imagine things.
               | 
               | So, it's the old ML join: It's just a bunch of if
               | statements. As others are pointing out, it's quite
               | probably that the model isn't the thing doing the heavy
               | lifting, it's the harness feeding the context. Which this
               | link shows that small models are just as capabable.
               | 
               | Which means: Given a appropiately informed senior
               | programmer and a day or two, I posit this is nothing more
               | spectacular than a for loop invoking a smaller, free,
               | local, LLM to find the same issues. It doesn't matter
               | what you think about the complexity, because the
               | "agentic" format can create a DAG that will be followable
               | by a small model. All that context you're taking in makes
               | oneshot inspections more probable, but much like how CPUs
               | have go from 0-5 ghz, then stalled, so too has the
               | context value.
               | 
               | Agent loops are going to do much the same with small
               | models, mostly from the context poisoning that happens
               | every time you add a token it raises the chance of false
               | positives.
        
               | tehryanx wrote:
               | I know you're right that there's a saturation point for
               | context size, but it's not just context size that the
               | larger models have, it's better grounding within that as
               | a result of stronger, more discriminative attention
               | patterns.
               | 
               | I'm not saying you're not going to drive confusion by
               | overloading context, but the number of tokens required to
               | trigger that failure mode in opus is going to be a lot
               | higher than the number for gpt-oss-20b.
               | 
               | I'm pretty sure a model that can run on a cellphone is
               | going to cap out it's context window long before opus or
               | mythos would hit the point of diminishing returns on
               | context overload. I think using a lower quality model
               | with far fewer / noisier weights and less precise
               | attention is going to drive false positives way before
               | adding context to a SOTA model will.
               | 
               | You can even see here, AISLE had to print a retraction
               | because someone checked their work and found that just
               | pointing gpt-oss-20b at the patched version generated FP
               | consistently:
               | https://x.com/ChaseBrowe32432/status/2041953028027379806
        
               | pertymcpert wrote:
               | Yeah...except Mythos's large context perf seems to be
               | much better than Opus 4.6.
        
           | lelanthran wrote:
           | > That's why their point is what the subheadline says, that
           | the moat is the system, not the model.
           | 
           | I'm skeptical; they provided a tiny piece of code and a hint
           | to the possible problem, and their system found the bug using
           | a small model.
           | 
           | That is hardly useful, is it? In order to get the same result
           | , they had to know both where the bug is and what the bug is.
           | 
           | All these companies in the business of "reselling tokens, but
           | with a markup" aren't going to last long. The only strategy
           | is "get bought out and cash out before the bubble pops".
        
           | epistasis wrote:
           | If that's the point they are making, let's see their false
           | positive rate that it produces on the entire codebase.
           | 
           | They measured false negatives on a handful of cases, but that
           | is not enough to hint at the system you suggest. And based on
           | my experiences with $$$ focused eval products that you can
           | buy right now, e.g. greptile, the false positive rate will be
           | so high that it won't be useful to do full codebase scans
           | this way.
        
             | zelphirkalt wrote:
             | How do we know the false positives for this "Mythos"
             | thingamabob? Since they didn't release it, and we cannot
             | reproduce it, are we to simply believe their word on this?
             | What if the author of the featured article simply made a
             | claim about that? We also simply believe their word? To me
             | these AI tech companies are not any more trustworthy than a
             | random blog author, maybe even less so, due to all the
             | shady stuff they are pulling and especially since they have
             | not released. Show or it didn't happen.
        
           | LordDragonfang wrote:
           | > That said, a well-designed scaffold naturally produces this
           | kind of scoped context through its targeting and iterative
           | prompting stages, which is exactly what both AISLE's and
           | Anthropic's systems do.
           | 
           | Unless the context they added to get the small model to find
           | it was generated fully by their own scaffold (which I assume
           | it was not, since they'd have bragged about it if it was),
           | either they're admitting theirs _isn 't_ well designed, or
           | they're outright lying.
           | 
           | People aren't missing the point, they're saying the point is
           | dishonest.
        
           | scotty79 wrote:
           | > Scoped context: Our tests gave models the vulnerable
           | function directly, often with contextual hints (e.g.,
           | "consider wraparound behavior").
           | 
           | To be fair, nothing stops anyone from feeding each function
           | of given codebase separately with one out of the predefined
           | set of hints.
           | 
           | It's just AST and a for loop. Calling it a system is a bit
           | much.
        
         | loire280 wrote:
         | > Anthropic's own scaffold is described in their technical
         | post: launch a container, prompt the model to scan files, let
         | it hypothesize and test, use ASan as a crash oracle, rank files
         | by attack surface, run validation. That is very close to the
         | kind of system we and others in the field have built, and we've
         | demonstrated it with multiple model families, achieving our
         | best results with models that are not Anthropic's. The value
         | lies in the targeting, the iterative deepening, the validation,
         | the triage, the maintainer trust. The public evidence so far
         | does not suggest that these workflows must be coupled to one
         | specific frontier model.
         | 
         | The argument in the article is that the framework to run and
         | analyze the software being tested is doing most of the work in
         | Anthropic's experiment, and that you can get similar results
         | from other models when used in the same way.
        
           | roywiggins wrote:
           | Maybe that's true, but they didn't actually show that that's
           | true, since they didn't try scaffolding smaller models in a
           | similar way at all.
        
         | Jcampuzano2 wrote:
         | The thing is with smaller cheaper models it is very possible to
         | simply take every file in a codebase, and prompt it asking for
         | it to find vulnerabilities.
         | 
         | You could even isolate it down to every function and create a
         | harness that provides it a chain of where and how the function
         | is used and repeat this for every single function in a
         | codebase.
         | 
         | For some very large codebases this would be unreasonable, but
         | many of the companies making these larger models do
         | realistically have the compute available to run a model on
         | every single function in most codebases.
         | 
         | You have the harness run this many times per file/function, and
         | then find ones that are consistently/on average pointed as as
         | possible vulnerability vectors, and then pass those on to a
         | larger model to inspect deeper and repeat.
         | 
         | Most of the work here wouldn't be the model, it'd be the
         | harness which is part of what the article alludes to.
        
           | loeg wrote:
           | > it is very possible to simply take every file in a
           | codebase, and prompt it asking for it to find
           | vulnerabilities.
           | 
           | My understanding (based on the Security, Cryptography,
           | Whatever podcast interview[0] -- which, by the way, go listen
           | to it) is that this is actually what Anthropic did with the
           | large model for these findings.
           | 
           | [0]: https://securitycryptographywhatever.com/2026/03/25/ai-
           | bug-f...
           | 
           | > I wrote a single prompt, which was the same for all of the
           | content management systems, which is, I would like you to
           | audit the security of this codebase. This is a CMS. You have
           | complete access to this Docker container. It is running.
           | Please find a bug. And then I might give a hint. "Please look
           | at this file." And I'll give different files each time I
           | invoke it in order to inject some randomness, right? Because
           | the model is gonna do roughly the same time each time you run
           | it. And so if I want to have it be really thorough, instead
           | of just running 100 times on the same project, I'll run it
           | 100 times, but each time say, "Oh, look at this login file,
           | look at this other thing." And just enumerate every file in
           | the project basically.
        
           | roywiggins wrote:
           | "small models can do this if you scaffold them right" might
           | be true, but it wasn't actually demonstrated in the post.
        
       | MaxLeiter wrote:
       | I think they key thing here is they "isolated the relevant code"
       | 
       | If the exploits exist in e.g. one file, great. But many complex
       | zerodays and exploits are chains of various bugs/behaviors in
       | complex systems.
       | 
       | Important research but I don't think it dispels anything about
       | Mythos
        
         | slopinthebag wrote:
         | Did Mythos identify vulnerabilities across files? Afaik Mythos
         | worked the same way, analysing a single file at a time.
        
         | davebren wrote:
         | Seems perfectly comparable to anthropic's method, they just
         | wrapped the same kind of prompt in a for loop.
        
       | JackYoustra wrote:
       | > Isolated the relevant code
       | 
       | I mean isn't that most of it? If you put a snippet of code in
       | front of me and said "there's probably a vulnerability here" I
       | could probably spend a few hours (a much lower METR time!) and
       | find it. It's a whole other ballgame to ask me with no context to
       | come up with an exploit.
        
         | kennywinker wrote:
         | Sure. But it's a computer. You can run "there's probably a
         | vulnerability here" as many times as you like. And it's easier
         | and cheaper to run it many times with a small open model than a
         | big frontier model.
         | 
         | It also sounds like that is how mythos works too. Which makes
         | sense - the linux kernel is too big to fit in context
        
           | JackYoustra wrote:
           | No, it sounds like mythos is just doing parallel
           | trajectories. that's pretty distinct!
        
       | amazingamazing wrote:
       | Did mythos isolate the code to begin with? Without a clear
       | methodology that can be attempted with another model the whole
       | thing is meaningless
        
         | aniceperson wrote:
         | to be fair, last post i saw from anthropic on finding linux
         | kernel vulnerability was a while loop per failed prompting
         | "there is a vulnerability here, find it" more important than
         | that, no frontier model can keep the entire linux kernel in
         | context, so there definitely is code isolation, either
         | explicitly or implicitly (the model itself delegates subagents
         | with smaller chunks of code)
        
         | loeg wrote:
         | No. How would it? Before the vulns were identified by Mythos,
         | no one knew what the relevant portion to isolate was.
        
         | bhouston wrote:
         | They did do one agent per code chunk, yes. But key is that
         | their agent had to identify when there was a vulnerability and
         | when there wasn't. This "small model" test only had to label
         | the known positive cases as positive -- which any function that
         | simply returns "true" can do. This whole test setup is annoying
         | because it proves nothing.
        
       | dist-epoch wrote:
       | Anthropic claim is not necessarily that Mythos found
       | vulnerabilities that other models couldn't but that it could
       | easily exploit them while previous models failed to do that:
       | 
       | > "Opus 4.6 is currently far better at identifying and fixing
       | vulnerabilities than at exploiting them." Our internal
       | evaluations showed that Opus 4.6 generally had a near-0% success
       | rate at autonomous exploit development. But Mythos Preview is in
       | a different league. For example, Opus 4.6 turned the
       | vulnerabilities it had found in Mozilla's Firefox 147 JavaScript
       | engine--all patched in Firefox 148--into JavaScript shell
       | exploits only two times out of several hundred attempts. We re-
       | ran this experiment as a benchmark for Mythos Preview, which
       | developed working exploits 181 times, and achieved register
       | control on 29 more.
        
         | rychu wrote:
         | If that was normal Opus, then it sounds to me like Mythos could
         | be a big model, instruction tuned, but without all the
         | safety/refusal part of training.
        
       | chirau wrote:
       | Their isolation approach is totally different from Mythos
       | approach though. Mythos had to evaluate whole code bases rather
       | than isolated sections. It's like saying one dog walked into the
       | Amazon jungle and found a tennis ball and then another team
       | isolated a 1 square kilometer radius that they knew the ball was
       | definitely in and found the same ball.
        
         | kennywinker wrote:
         | I don't think mythos can ingest an entire codebase into
         | context. So it's spinning off sub-agents to process chunks.
         | Which supports their thesis: the harness is the moat. The
         | tooling is whats important, the model is far far less
         | important.
        
           | bhouston wrote:
           | Mythos was clear it was one agent per chunk. But this
           | positive confirming results do not actually disprove anytime
           | with Mythos, because it is only one side of the discriminator
           | challenge - you got positives, but we do not know your false
           | positive rate and your false negative rate.
        
             | kennywinker wrote:
             | In TFA they talk a fair bit about how different models
             | perform wrt false positives:
             | 
             | "The results show something close to inverse scaling:
             | small, cheap models outperform large frontier ones."
        
               | mofeien wrote:
               | These results were based on "a trivial snippet from the
               | OWASP benchmark". In the section "caveats and
               | limitations" they state that sonnet 4.6 and opus 4.6 now
               | pass.
               | 
               | And they decided to base the false positive examination
               | on a single snippet of a publicly known benchmark
               | question (that small models are known to be heavily fine
               | tuned for) instead of the real use case of finding actual
               | vulnerabilities across an entire codebase by using a for
               | loop and checking the false positive rate there.
               | 
               | This is disingenuous at best, or even misleading by
               | omission if the second approach _was_ done but not
               | mentioned because it just confirmed that the false
               | positive rate of small models is enormous. Given how all
               | seven small models identified the FreeBSD Bug when
               | pointed to it, and how how 6/7 small models still
               | identified the "bug" even after the patch was applied,
               | that second outcome seems likely...
        
           | eiens wrote:
           | Let's suppose that's true
           | 
           | What's so special about the harness - why wouldn't others be
           | able to replicate it?
        
         | hakanderyal wrote:
         | Even that would be more meaningful test. They basically coated
         | the ball with a strong smell, then they prepped the dog with
         | that smell, then set it loose in a 5x5 meter area.
         | 
         | "Our tests gave models the vulnerable function directly, often
         | with contextual hints (e.g., "consider wraparound behavior")."
        
       | johnfn wrote:
       | The Anthropic writeup addresses this explicitly:
       | 
       | > This was the most critical vulnerability we discovered in
       | OpenBSD with Mythos Preview after a thousand runs through our
       | scaffold. Across a thousand runs through our scaffold, the total
       | cost was under $20,000 and found several dozen more findings.
       | While the specific run that found the bug above cost under $50,
       | that number only makes sense with full hindsight. Like any search
       | process, we can't know in advance which run will succeed.
       | 
       | Mythos scoured the entire continent for gold and found some. For
       | these small models, the authors pointed at a particular acre of
       | land and said "any gold there? eh? eh?" while waggling their
       | eyebrows suggestively.
       | 
       | For a true apples-to-apples comparison, let's see it sweep the
       | entire FreeBSD codebase. I hypothesize it will find the exploit,
       | but it will also turn up so much irrelevant nonsense that it
       | won't matter.
        
         | SoftTalker wrote:
         | How much of that is simply scale? Anthropic threw probably an
         | entire data center at analyzing a code base. Has anyone done
         | the same with a "small" model?
        
           | jstanley wrote:
           | It's still useful if $20k of consultants would be less
           | effective.
        
         | hellcow wrote:
         | It seems feasible to use a small/cheap model to flag possible
         | vulnerabilities, and then use a more expensive model to do a
         | second-pass to confirm those, rather than on every file. Could
         | dramatically reduce the total cost and speed up the process.
        
           | conception wrote:
           | Does it? I don't see quality from small models being high
           | enough to be able to effectively scour a code based like
           | this.
        
         | notnullorvoid wrote:
         | > I hypothesize it will find the exploit, but it will also turn
         | up so much irrelevant nonsense that it won't matter.
         | 
         | The trick with Mythos wasn't that it didn't hallucinate
         | nonsense vulnerabilities, it absolutely did. It was able to
         | verify some were real though by testing them.
         | 
         | The question is if smaller models can verify and test the
         | vulnerabilities too, and can it be done cheaper than these
         | Mythos experiments.
        
           | iririririr wrote:
           | so it's just better at hallucinations, but they added
           | discrete code that works as a fuzzer/verifier?
        
           | bredren wrote:
           | The article positions the smaller models as capable under
           | expert orchestration, which to be any kind of comparable must
           | include validation.
        
             | Aurornis wrote:
             | Calling it "expert orchestration" is misleading when they
             | were pointing it at the vulnerable functions and giving it
             | hints about what to look for because they already knew the
             | vulnerability.
        
               | cyanydeez wrote:
               | You know for loops exist and you can run opencode against
               | any section of code with just a small amount of
               | templating, right? There's zero stopping you from writing
               | a harness that does what you're saying.
        
           | hibikir wrote:
           | People often undervalue scaffolding. I was looking at a bug
           | yesterday, reported by a tester. He has access to Opus, but
           | he's looking through a single repo, and Amazon Q. It provided
           | some useful information, but the scaffolding wasn't good
           | enough.
           | 
           | I took its preliminary findings into Claude Code with the
           | same model. But in mine it knows where every adjacent system
           | is, the entire git history, deployment history, and state of
           | the feature flags. So instead of pointing at a vague problem,
           | it knew which flag had been flipped in a different service,
           | see how it changed behavior, and how, if the flag was flipped
           | in prod, it'd make the service under testing cry, and which
           | code change to make to make sure it works both ways.
           | 
           | It's not as if a modern Opus is a small model: Just a
           | stronger scaffold, along with more CLI tools available in the
           | context.
           | 
           | The issue here in the security testing is to know exactly
           | what was visible, and how much it failed, because it makes a
           | huge difference. A middling chess player can find amazing
           | combinations at a good speed when playing puzzle rush: You
           | are handed a position where you know a decisive combination
           | exist, and that it works. The same combination, however,
           | might be really hard to find over the board, because in a
           | typical chess game, it's rare for those combinations to
           | exist, and the energy needed to thoroughly check for them,
           | and calculate all the way through every possible thing. This
           | is why chess grandmasters would consider just being able to
           | see the computer score for a position to be massive cheating:
           | Just knowing when the last move was a blunder would be a
           | decisive advantage.
           | 
           | When we ask a cheap model to look for a vulnerability with
           | the right context to actually find it, we are already priming
           | it, vs asking to find one when there's nothing.
        
         | celeritascelery wrote:
         | That was my thought exactly. If small models can find these
         | same vulnerabilities, and your company is trying to find
         | vulnerabilities, why didn't you find them?
        
           | rakejake wrote:
           | Maybe they did use small models but you couldn't make the
           | front page of HN with something like this until Anthropic
           | made a big fuss out of it. Or perhaps it is just a question
           | of compute. Not everyone has 20k$ or the GPU arsenal to task
           | models to find vulnerabilities which may/may not be correct?
           | 
           | Unless Anthropic makes it known exactly what model +
           | harness/scaffolding + prompt + other engineering they did,
           | these comparisons are pointless. Given the AI labs' general
           | rate of doomsday predictions, who really knows?
        
             | replygirl wrote:
             | papers are always coming out saying smaller models can do
             | these amazing and terrifying things if you give them highly
             | constrained problems and tailored instructions to bias them
             | toward a known solution. most of these don't make the front
             | page because people are rightfully unimpressed
        
           | echelon wrote:
           | Who is spending millions of dollars on small models to find
           | vulns? Nobody else is selling here or has the budget to sell
           | quite like this.
           | 
           | Anthropic spends millions - maybe significantly more.
           | 
           | Then when they know where they are, they spend $20k to show
           | how effective it is in a patch of land.
           | 
           | They engineered this "discovery".
           | 
           | What the small teams are doing is fair - it's just a scaled
           | down version of what Anthropic already did.
        
             | paulddraper wrote:
             | > What the small teams are doing is fair - it's just a
             | scaled down version of what Anthropic already did.
             | 
             | Do they find novel items? Or do they copy the areas already
             | found by others?
        
           | petters wrote:
           | They have found a large number in OpenSSl
        
           | jerf wrote:
           | I speculatively fired Claude Opus 4.6 at some code I knew
           | very well yesterday as I was pondering the question. This
           | code has been professionally reviewed about a year ago and
           | came up fairly clean, with just a minor issue in it.
           | 
           | Opus "found" 8 issues. Two of them looked like they were
           | probably realistic but not really that big a deal in the
           | context it operates in. It labelled one of them as minor, but
           | the other as major, and I'm pretty sure it's wrong about it
           | being "major" even if is correct. Four of them I'm quite
           | confident were just wrong. 2 of them would require
           | substantial further investigation to verify whether or not
           | they were right or wrong. I think they're wrong, but I admit
           | I couldn't prove it on the spot.
           | 
           | It tried to provide exploit code for some of them, none of
           | the exploits would have worked without some substantial
           | additional work, even if what they were exploits for was
           | correct.
           | 
           | In practice, this isn't a huge change from the status quo.
           | There's all kinds of ways to get lots of "things that may be
           | vulnerabilities". The assessment is a bigger bottleneck than
           | the suspicions. AI providing "things that may be an issue" is
           | not useless by any means but it doesn't necessarily create a
           | phase change in the situation.
           | 
           | An AI that could automatically do all that, write the
           | exploits, and then successfully _test_ the exploits, refine
           | them, and turn the whole process into basically  "push
           | button, get exploit" is a total phase change in the industry.
           | If it in fact can do that. However based on the current
           | state-of-the-art in the AI world I don't find it very hard to
           | believe.
           | 
           | It is a frequent talking point that "security by obscurity"
           | isn't really security, but in reality, yeah, it really is. An
           | unknown but presumably staggering number of security bugs of
           | every shape and size are out there in the world, protected
           | solely by the fact that no human attacker has time to look at
           | the code. And this has _worked_ up until this point, because
           | the attackers have been bottlenecked on their own attention
           | time. It 's kind of just been "something everyone knows" that
           | any nation-state level actor could get into pretty much
           | anything they wanted if they just tried hard enough, but
           | "nation-state level" actor attention, despite how much is
           | spent on it, has been quite limited relative to the torrent
           | of software coming out in the world.
           | 
           | Unblocking the attackers by letting them simply purchase
           | "nation-state level actor"-levels of attention in bulk is
           | _huge_. For what such money gets them, it 's cheap already
           | today and if tokens were to, say, get an order of magnitude
           | cheaper, it would be effectively negligible for a lot of
           | organizations.
           | 
           | In the long run this will probably lead to much more secure
           | software. The transition period from this world to that is
           | going to be _total chaos_.
           | 
           | ... again, assuming their assessment of its capabilities is
           | accurate. I haven 't used it. I can't attest to that. But if
           | it's even half as good as what they say, yes, it's a _huge
           | huge huge_ deal and anyone who is even remotely worried about
           | security needs to pay attention.
        
         | alpha_squared wrote:
         | This is addressed elsewhere in the comments, but it appears
         | this is actually a direct comparison to how Anthropic got their
         | Mythos headline results.
         | 
         | https://news.ycombinator.com/item?id=47732322
        
           | Aurornis wrote:
           | How is that a direct comparison? The link you gave has a
           | quote that says it's not:
           | 
           | > Scoped context: Our tests gave models the vulnerable
           | function directly, often with contextual hints (e.g.,
           | "consider wraparound behavior"). A real autonomous discovery
           | pipeline starts from a full codebase with no hints
           | 
           | They pointed the models at the known vulnerable functions and
           | gave them a hint. The hint part is what really breaks this
           | comparison because they were basically giving the model the
           | answer.
        
             | cyanydeez wrote:
             | Does no one defending mythos understand how nested
             | foreloops work?
             | 
             | loop through each repo: loop through each file: opencode
             | command /find_wraparoundvulnerability next file next repo
             | 
             | I can run this on my local LLM and sure, I gotta wait some
             | time for it to complete, but I see zero distinguishing
             | facts here.
        
               | u_fucking_dork wrote:
               | Please do so, looking forward to your write up
        
               | Dylan16807 wrote:
               | The question is how customized those hints were. That
               | changes whether looping over an entire code base is
               | possible or not.
        
               | johnfn wrote:
               | No one is saying your nested for loop idea because it
               | won't actually work in practice. In short, the signal to
               | noise ratio will be too high - you will need to comb
               | through a ton of false positives in order to find
               | anything valuable, at which point it stops looking like
               | "automated security research" and it starts looking like
               | "normal security research".
               | 
               | If you don't believe me, you should try it yourself, it's
               | only a couple of dollars. Hey, maybe you're right, and
               | you can prove us all wrong. But I'd bet you on great odds
               | that you're not.
        
               | yorwba wrote:
               | When people criticize Aisle's methodology, they aren't
               | "defending Mythos," they're bashing Aisle for their
               | disingenuous claims.
        
               | fulafel wrote:
               | Aisle said they pointed it at the function, not the file.
               | So, the nr of LLM turns would be something like nr of
               | functions * nr of possible hints * nr of repos.
               | 
               | Could indeed be a useful exercise to benchmark the cost.
               | 
               | This would still be more limied, since many
               | vulnerabilities are apparent only when you consider more
               | context than one function to discover the vulnerability.
               | I think there were those kinds of vulnerabilities in the
               | published materials. So maybe the Aisle case is also
               | picking the low hanging fruit in this respect.
        
         | yorwba wrote:
         | We don't even need to hypothesize that much on the irrelevant
         | nonsense, since they helpfully provide data with the detected
         | vulnerability patched: https://aisle.com/blog/ai-cybersecurity-
         | after-mythos-the-jag... and half of the small models they
         | touted as finding the vulnerability still found it in the
         | patched code in 3/3 runs. A model that finds a vulnerability
         | 100% of the time even when there is none is just as informative
         | as a model that finds a vulnerability 0% of the time even when
         | there is one. You could replace it with a rock that has
         | "There's a vulnerability somewhere." engraved on it.
         | 
         | They're a company selling a system for detecting
         | vulnerabilities reliant on models trained by others, so they're
         | strongly incentivized to claim that the moat is in the system,
         | not the model, and this post really puts the thumb on the
         | scale. They set up a test that can hardly distinguish between
         | models (just three runs, really??) unless some are completely
         | broken or work perfectly, the test indeed suggests that some
         | are completely broken, and then they try to spin it as a win
         | anyway!
         | 
         | A high false-positive rate isn't necessarily an issue if you
         | can produce a working PoC to demonstrate the true positives,
         | where they kinda-sorta admit that you might need a stronger
         | model for this (a.k.a. what they can't provide to their
         | customers).
         | 
         | Overall I rate Aisle intellectually dishonest hypemongers
         | talking their own book.
        
         | kilpikaarna wrote:
         | Wasn't the scaffolding for the Mythos run basically a line of
         | bash that loops through every file of the codebase and prompts
         | the model to find vulnerabilities in it? That sounds pretty
         | close to "any gold there?" to me, only automated.
         | 
         | Have Anthropic actually said anything about the amount of false
         | positives Mythos turned up?
         | 
         | FWIW, I saw some talk on Xitter (so grain of salt) about people
         | replicating their result with other (public) SotA models, but
         | each turned up only a subset of the ones Mythos found. I'd say
         | that sounds plausible from the perspective of Mythos being an
         | incremental (though an unusually large increment perhaps)
         | improvement over previous models, but one that also brings with
         | it a correspondingly significant increase in complexity.
         | 
         | So the angle they choose to use for presenting it and the
         | subsequent buzz is at least part hype -- saying "it's too
         | powerful to release publicly" sounds a lot cooler than "it
         | costs $20000 to run over your codebase, so we're going to offer
         | this directly to enterprise customers (and a few token open
         | source projects for marketing)". Keep in mind that the examples
         | in Nicholas Carlini's presentation were using Opus, so security
         | is clearly something they've been working on for a while (as
         | they should, because it's a huge risk). They didn't just
         | suddenly find themselves having accidentally created a super
         | hacker.
        
           | johnfn wrote:
           | > Wasn't the scaffolding for the Mythos run basically a line
           | of bash that loops through every file of the codebase and
           | prompts the model to find vulnerabilities in it? That sounds
           | pretty close to "any gold there?" to me, only automated.
           | 
           | But the entire value is that it _can_ be automated. If you
           | try to automate a small model to look for vulnerabilities
           | over 10,000 files, it 's going to say there are 9,500 vulns.
           | Or none. Both are worthless without human intervention.
           | 
           | I definitely breathed a sigh of relief when I read it was
           | $20,000 to find these vulnerabilities with Mythos. But I also
           | don't think it's hype. $20,000 is, optimistically, a tenth
           | the price of a security researcher, and that shift does
           | change the calculus of how we should think about security
           | vulnerabilities.
        
             | amazingamazing wrote:
             | Citation needed for basically all of this. You basically
             | are creating a double standard for small models vs
             | mythos...
        
               | johnfn wrote:
               | The citation is the Anthropic writeup.
        
               | amazingamazing wrote:
               | They did not say what you are saying...
               | 
               | > If you try to automate a small model to look for
               | vulnerabilities over 10,000 files, it's going to say
               | there are 9,500 vulns.
        
               | johnfn wrote:
               | What I am saying is that the approach the Anthropic
               | writeup took and the approach Aisle took are very
               | different. The Aisle approach is vastly easier on the
               | LLM. I don't think I need a citation for that. You can
               | just read both writeups.
               | 
               | The "9500" quote is my conjecture of what might happen if
               | they fix their approach, but the burden of proof is
               | definitely not on me to actually fix their writeup and
               | spend a bunch of money to run a new eval! They are the
               | ones making a claim on shaky ground, not me.
        
               | cycomanic wrote:
               | So you can't imagine anything between bruteforce scan the
               | whole codebase and cut everything up in small chunks and
               | scan only those?
               | 
               | You don't think that security companies (and likely these
               | guys as well) develop systems for doing this stuff?
               | 
               | I'm not a security researcher and I can imagine a harness
               | that first scans the codebase and describes the API, then
               | another agent determines which functions should be looked
               | at more closely based on that description, before handing
               | those functions to another small llm with the appropriate
               | context. Then you can even use another agent to evaluate
               | the result to see if there are false positives.
               | 
               | I would wager that such a system would yield better
               | results for a much lower price.
               | 
               | Instead we are talking about this marketing exercise
               | "oohh our model is so dangerous it can't be released, and
               | btw the results can't be independently verified either"
        
               | johnfn wrote:
               | I explained why this won't work elsewhere in the
               | thread[1].
               | 
               | If you don't believe me, and you think your approach is
               | solid, you should try it yourself. It's only a couple of
               | dollars, and it would be extremely popular -- just look
               | at how popular this article, using improper methodology,
               | was! Hey, maybe you're right, and you can prove us all
               | wrong. But I'd bet you on great odds that you're not.
               | 
               | [1]: https://news.ycombinator.com/item?id=47734710
        
             | integralid wrote:
             | >Or none
             | 
             | We already know this is not true, because small models
             | found the same vulnerability.
        
               | tptacek wrote:
               | No, they didn't. They _distinguished_ it, when presented
               | with it. Wildly different problem.
        
               | enraged_camel wrote:
               | Yeah. And it is totally depressing that this article got
               | voted to the top of the front page. It means people
               | aren't capable of this most basic reasoning so they
               | jumped on the "aha! so the mythos announcement _was_ just
               | marketing!!"
        
               | woeirua wrote:
               | Yeah. Extremely disappointing.
        
               | BoiledCabbage wrote:
               | > because small models found the same vulnerability.
               | 
               | With a ton of extra support. Note this key passage:
               | 
               | >We isolated the vulnerable svc_rpc_gss_validate
               | function, provided architectural context (that it handles
               | network-parsed RPC credentials, that oa_length comes from
               | the packet), and asked eight models to assess it for
               | security vulnerabilities.
               | 
               | Yeah it can find a needle in a haystack without false
               | positives, if you first find the needle yourself, tell it
               | exactly where to look, explain all of the context around
               | it, remove most of the hay and then ask it if there is a
               | needle there.
               | 
               | It's good for them to continue showing ways that small
               | models can play in this space, but in my read their post
               | is fairly disingenuous in saying they are comparable to
               | what Mythos did.
               | 
               | I mean this is the start of their prompt, followed by
               | only 27 lines of the actual function:
               | 
               | > You are reviewing the following function from FreeBSD's
               | kernel RPC subsystem
               | (sys/rpc/rpcsec_gss/svc_rpcsec_gss.c). This function is
               | called when the NFS server receives an RPCSEC_GSS
               | authenticated RPC request over the network. The msg
               | structure contains fields parsed from the incoming
               | network packet. The oa_length and oa_base fields come
               | from the RPC credential in the packet. MAX_AUTH_BYTES is
               | defined as 400 elsewhere in the RPC layer.
               | 
               | The original function is 60 lines long, they ripped out
               | half of the function in that prompt, including additional
               | variables presumably so that the small model wouldn't get
               | confused / distracted by them.
               | 
               | You can't really do anything more to force the issue
               | except maybe include in the prompt the type of vuln to
               | look for!
               | 
               | It's great they they are trying to push small models, but
               | this write up really is just borderline fake. Maybe it
               | would actually succeed, but we won't know from that. Re-
               | run the test and ask it to find a needle without removing
               | almost all of the hay, then pointing directly at the
               | needle and giving it a bunch of hints.
               | 
               | The prompt they used:
               | https://github.com/stanislavfort/mythos-jagged-
               | frontier/blob...
               | 
               | Compare it to the actual function that's twice as long.
        
               | apgwoz wrote:
               | The benefit here is reducing the time to find
               | vulnerabilities; faster than humans, right? So if you can
               | rig a harness for each function in the system, by first
               | finding where it's used, its expected input, etc, and
               | doing that for all functions, does it discover
               | vulnerabilities faster than humans?
               | 
               | Doesn't matter that they isolated one thing. It matters
               | that the context they provided was discoverable by the
               | model.
        
               | woeirua wrote:
               | There is absolutely zero reason to believe you could use
               | this same approach to find and exploit vulns without
               | Mythos finding them first. We already know that older
               | LLMs can't do what Mythos has done. Anthropic and others
               | have been trying for years.
        
               | nozzlegear wrote:
               | > _There is absolutely zero reason to believe you could
               | use this same approach to find and exploit vulns without
               | Mythos finding them first._
               | 
               | There's one huge reason to believe it: we can actually
               | use small models, but we cant use Anthropic's special
               | marketing model that's too dangerous for mere mortals.
        
               | Filligree wrote:
               | If all you have is a spade, that is _not_ evidence that
               | spades are good for excavating an entire hill.
        
               | apgwoz wrote:
               | It takes longer, but a spade is better than bare hands.
               | The goal is to speed up finding valid vulnerabilities,
               | and be faster than humans can do it.
        
               | naasking wrote:
               | > If all you have is a spade, that is _not_ evidence that
               | spades are good for excavating an entire hill.
               | 
               | If you have an automated spade, that's still often better
               | for excavating that hill than you using a shovel by hand.
        
               | apgwoz wrote:
               | Why? They claim this small model found a bug given some
               | context. I assume the context wasn't "hey! There's a very
               | specific type of bug sitting in this function when
               | certain conditions are met."
               | 
               | We keep assuming that the models need to get bigger and
               | better, and the reality is we've not exhausted the ways
               | in which to use the smaller models. It's like the
               | Playstation 2 games that came out 10 years later. Well
               | now all the tricks were found, and everything improved.
        
               | usef- wrote:
               | If this were true, we're essentially saying that no one
               | tried to scan vulnerabilities using existing models,
               | despite vulnerabilities being extremely lucrative and a
               | large professional industry. Vulnerability research has
               | been one of the single most talked about risks of
               | powerful AI so it wasn't exactly a novel concept, either.
               | 
               |  _If_ it is true that existing models can do this, it
               | would imply that LLMs are being under marketed, not over
               | marketed, since industry didn 't think this was worth
               | trying previously(?). Which I suspect is not the opinion
               | of HN upvoters here.
        
               | apgwoz wrote:
               | I use the models to look for vulnerabilities all the
               | time. I find stuff often. Have I tried to do build a new
               | harness, or develop more sophisticated techniques? No. I
               | suspect there are some spending lots of tokens developing
               | more sophisticated strategies, in the same way software
               | engineers are seeking magical one-shot harnesses.
        
               | salawat wrote:
               | ...The absolute last thing I'd want to do is feed AI
               | companies my proprietary codebase. Which is _exactly_
               | what using these things to scan for vulns requires. You
               | want to hand me the weights, and let me set up the
               | hardware to run and serve the thing in my network
               | boundary with no calling home to you? That 'd be one
               | thing. Literally handing you the family jewels? Hell no.
               | Not with the non-existence of professional discretion
               | demonstrated by the tech industry. No way, no how.
               | 
               | To be honest, this just sounds like a ploy to get their
               | hands on more training data through fear. Not buying it,
               | and they clearly ain't interested in selling in good
               | faith either. So DoA from my point-of-view anyways.
        
               | kenjackson wrote:
               | I don't think these companies are hurting for access to
               | code.
        
               | cycomanic wrote:
               | From the article:
               | 
               | >At AISLE, we've been running a discovery and remediation
               | system against live targets since mid-2025: 15 CVEs in
               | OpenSSL (including 12 out of 12 in a single security
               | release, with bugs dating back 25+ years and a CVSS 9.8
               | Critical), 5 CVEs in curl, over 180 externally validated
               | CVEs across 30+ projects spanning deep infrastructure,
               | cryptography, middleware, and the application layer.
               | 
               | So there is pretty good evidence that yes you can use
               | this approach. In fact I would wager that running a more
               | systematic approach will yield better results than just
               | bruteforcing, by running the biggest model across
               | everything. It definitely will be cheaper.
        
             | SpicyLemonZest wrote:
             | What the source article claims is that small models are
             | _not_ uniformly worse at this, and in fact they might be
             | better at certain classes of false positive exclusion. This
             | is what Test 1 seems to show.
             | 
             | (I would emphasize that the article doesn't claim and I
             | don't believe that this proves Mythos is "fake" or doesn't
             | matter.)
        
             | sweezyjeezy wrote:
             | > But the entire value is that it can be automated. If you
             | try to automate a small model to look for vulnerabilities
             | over 10,000 files, it's going to say there are 9,500 vulns.
             | Or none.
             | 
             | 'Or none' is ruled out since it found the same
             | vulnerability - I agree that there is a question on
             | precision on the smaller model, but barring further
             | analysis it just feels like '9500' is pure vibes from
             | yourself? Also (out of interest) did Anthropic post their
             | false-positive rate?
             | 
             | The smaller model is clearly the more automatable one IMO
             | if it has comparable precision, since it's just so much
             | cheaper - you could even run it multiple times for
             | consensus.
        
               | johnfn wrote:
               | Admittedly just vibes from me, having pointed small
               | models at code and asked them questions, no extensive
               | evaluation process or anything. For instance, I recall
               | models thinking that every single use of `eval` in
               | javascript is a security vulnerability, even something
               | obviously benign like `eval("1 + 1")`. But then I'm only
               | posting comments on HN, I'm not the one writing an
               | authoritative thinkpiece saying Mythos actually isn't a
               | big deal :-)
        
               | argee wrote:
               | With LLMs (and colleagues) it might be a legitimate
               | problem since they would load that eval into context and
               | maybe decide it's an acceptable paradigm in your
               | codebase.
        
               | bloaf wrote:
               | I remember a study from a while back that found something
               | like "50% of 2nd graders think that french fries are made
               | out of meat instead of potatoes. Methodology: we asked
               | kids if french fries were meat or potatoes."
               | 
               | Everyone was going around acting like this meant 50% of
               | 2nd graders were stupid with terrible parents. (Or,
               | conversely, that 50% of 2nd graders were geniuses for
               | "knowing" it was potatoes at all)
               | 
               | But I think that was the wrong conclusion.
               | 
               | The right conclusion was that _all_ the kids guessed and
               | they had a 50% chance of getting it right.
               | 
               | And I think there is probably an element of this going on
               | with the small models vs big models dichotomy.
        
               | Kye wrote:
               | I think it also points to the problem of implicit
               | assumptions. Fish is meat, right? Except for historical
               | reasons, the grocery store's marketing says "Fish &
               | Meat."
               | 
               | And then there's nut meats. Coconut meat. All the kinds
               | of meat from before meat meant the stuff in animals. The
               | meat of the problem. Meat and potatoes issues.
               | 
               | If you asked that question before I'd picked up those
               | implicit assumptions, or if I never did, I would have to
               | guess.
        
               | roxolotl wrote:
               | I've got many catholic relatives that describe themselves
               | as vegetarians and eat fish. Language can be surprisingly
               | imprecise and dependent upon tons of assumptions.
        
               | alwillis wrote:
               | > I've got many catholic relatives that describe
               | themselves as vegetarians and eat fish
               | 
               | Those are pescatarians.
               | 
               | It's like how a tomato is a fruit, but it's used as a
               | vegetable, meat has traditionally been the flesh of warm-
               | blooded animals. Fish is the flesh of cold-blooded
               | animals, making it meat but due to religious reasons it's
               | not considered meat.
        
               | roxolotl wrote:
               | Right exactly. The point is that dictionary definitions
               | don't always align with cultural ones.
        
               | jorvi wrote:
               | My proof-in-pudding test is still the fact that we
               | haven't seen gigantic mass firings at tech companies, nor
               | a massive acceleration on quality or breadth (not
               | quantity!) of development.
               | 
               | Microsoft has been going heavy on AI for 1y+ now. But
               | then they replace their cruddy native Windows Copilot
               | application with an Electron one. If tests and dev only
               | has marginal cost now, why aren't they going all in on
               | writing extremely performant, almost completely bug-free
               | native applications everywhere?
               | 
               | And this repeats itself across all big tech or AI hype
               | companies. They all have these supposed earth-shattering
               | gains in productivity but then.. there hasn't been
               | anything to show for that in years? Despite that whole
               | subsect of tech plus big tech dropping trillions of
               | dollars on it?
               | 
               | And then there is also the really uncomfortable question
               | for all tech CEOs and managers: LLMs are better at
               | 'fuzzy' things like writing specs or documentation than
               | they are at writing code. And LLMs are supposedly
               | godlike. Leadership is a fuzzy thing. At some point the
               | chickens will come to roost and tech companies with LLM
               | CEOs / managers and human developers or even completely
               | LLM'd will outperform human-led / managed companies. The
               | capital class will jeer about that for a while, but the
               | cost for tokens will continue to drop to near zero. At
               | that point, they're out of leverage too.
        
               | MidnightRider39 wrote:
               | Leadership is also a very human thing. I think most
               | people would balk at the idea of being led by an LLM.
               | 
               | One of the main functions of leaders (should be) is to
               | assume responsibility for decisions and outcomes. A
               | computer cant do that.
               | 
               | And finally why should someone in power choose to replace
               | themselves?
        
               | eiens wrote:
               | Someone in power doesn't get to choose - the board of
               | directors do. Who's job is to act in the best interest of
               | shareholders.
               | 
               | Firms tend to follow peers in an industry - once one
               | blinks the rest follow.
        
               | MidnightRider39 wrote:
               | The board of directors are also people in power - why not
               | replace them with an LLM as well if it works so well for
               | CEOs?
        
               | eru wrote:
               | > Someone in power doesn't get to choose - the board of
               | directors do. Who's job is to act in the best interest of
               | shareholders.
               | 
               | Alas, shareholder value is a great ideal, but it tends to
               | be honoured in practice rather less strictly.
               | 
               | As you can also see when sudden competition leads to
               | rounds of efficiency improvements, cost cutting and
               | product enhancements: even without competition, a penny
               | saved is a penny earned for shareholders. But only when
               | fierce competition threatens to put managers' jobs at
               | risk, do they really kick into overdrive.
        
               | dbdr wrote:
               | > Someone in power doesn't get to choose - the board of
               | directors do
               | 
               | Since the board of directors can decide to replace the
               | CEO, it's not the CEO who holds the (ultimate) power,
               | it's the board of directors.
        
               | jsjohnst wrote:
               | Since the majority shareholder(s) can decide to replace
               | the board of directors, it's not the board of directors
               | who holds the (ultimate) power, it's the majority
               | shareholder(s).
        
               | johnfn wrote:
               | Your proof-in-pudding test seems to assume that AI is
               | binary -- either it accelerates everyone's development
               | 100x ("let's rewrite every app into bug-free native
               | applications") or nothing ("there hasn't been anything to
               | show for that in years"). I posit reality is somewhere in
               | between the two.
        
               | eiens wrote:
               | LLM's are capable of searching information spaces and
               | generating some outputs that one can use to do their job.
               | 
               | But it's not taking anyone's job, ever. People are not
               | bots, a lot of the work they do is tacit and goes well
               | beyond the capabilities and abilities of llm's.
               | 
               | Many tech firms are essentially mature and are currently
               | using too much labour. This will lead to a natural cycle
               | of lay offs if they cannot figure out projects to
               | allocate the surplus labour. This is normal and healthy -
               | only a deluded economist believes in 'perfect' stuff.
        
               | johnfn wrote:
               | In this entire thread of conversation, I never said that
               | LLMs would take people's jobs, and that is not something
               | I believe.
        
               | ipaddr wrote:
               | "it's not taking anyone's job, ever"
               | 
               | It has already and that doesn't mean new jobs haven't
               | been created or that those new jobs went to those who
               | lost their jobs.
        
               | locknitpicker wrote:
               | > Microsoft has been going heavy on AI for 1y+ now. But
               | then they replace their cruddy native Windows Copilot
               | application with an Electron one.
               | 
               | This.
               | 
               | Also, Microsoft is going heavy on AI but it's primarily
               | chatbot gimmicks they call copilot agents, and they need
               | to deeply integrate it with all their business products
               | and have customers grant access to all their
               | communications and business data to give something for
               | the chatbot to work with. They go on and on in their AI
               | your with their example on how a company can work on
               | agents alone, and they tell everyone their job is
               | obsoleted by agents, but they don't seem to dogfood any
               | of their products.
        
               | nopinsight wrote:
               | > LLMs are better at 'fuzzy' things like writing specs or
               | documentation than they are at writing code.
               | 
               | At least for writing specs, this is clearly not true. I
               | am a startup founder/engineer who has written a lot of
               | code, but I've written less and less code over the last
               | couple of years and very little now. Even much of the
               | code review can be delegated to frontier models now (if
               | you know which ones to use for which purpose).
               | 
               | I still need to guide the models to write and revise
               | specs a great deal. Current frontier LLMs are great at
               | verifiable things (quite obvious to those who know how
               | they're trained), including finding most bugs. They are
               | still much less competent than expert humans at
               | understanding many 'softer' aspects of business and user
               | requirements.
        
               | naasking wrote:
               | > My proof-in-pudding test is still the fact that we
               | haven't seen gigantic mass firings at tech companies
               | 
               | Jevon's paradox.
        
               | mlmonkey wrote:
               | > My proof-in-pudding test is still the fact that we
               | haven't seen gigantic mass firings at tech companies
               | 
               | This assumes that companies will announce such mass
               | firings (yeah, I'm aware of WARN Act); when in reality
               | they will steadily let go of people for various reasons
               | (including "performance").
               | 
               | From my (tech heavy) social circle, I have noticed an
               | uptick in the number of people suddenly becoming
               | unemployed.
        
               | ummonk wrote:
               | What's a situation where one needs to use `eval` in
               | benign way in JS? If something is precomputable (e.g.
               | `eval("1 + 1")` can just be replaced by 2), then it
               | should be precomputed. If it's not precomputable then
               | it's dependent on input and thus hardly benign -- you'll
               | need to carefully verify that the inputs are properly
               | sanitized.
        
               | idopmstuff wrote:
               | > 'Or none' is ruled out since it found the same
               | vulnerability
               | 
               | It's not, though. It wasn't asked to find vulnerabilities
               | over 10,000 files - it was asked to find a vulnerability
               | in the one particular place in which the researchers knew
               | there was a vulnerability. That's not proof that it would
               | have found the vulnerability if it had been given a much
               | larger surface area to search.
        
               | sweezyjeezy wrote:
               | I don't think the LLM was asked to check 10,000 files
               | given these models' context windows. I suspect they went
               | file by file too.
               | 
               | That's kind of the point - I think there's three
               | scenarios here
               | 
               | a) this just the first time an LLM has done such a
               | thorough minesweeping b) previous versions of Claude did
               | not detect this bug (seems the least likely) c) Anthropic
               | have done this several times, but the false positive rate
               | was so high that they never checked it properly
               | 
               | Between a) and c) I don't have a high confidence either
               | way to be honest.
        
             | siva7 wrote:
             | Except you would need about 10,000 security researches in
             | parallel to inspect the whole FreeBSD codebase. So about
             | 200 million dollars at least.
        
             | mnicky wrote:
             | Also, what is $20,000 today can be $2000 next year. Or
             | $20...
             | 
             | See e.g. https://epoch.ai/data-insights/llm-inference-
             | price-trends/
        
               | sumeno wrote:
               | Or $200,000 for consumers when they have to make a profit
        
               | philipallstar wrote:
               | Good point. This is why consumer phones have got much
               | worse since 2005 and now cost millions of dollars.
        
               | ijk wrote:
               | With the way the chip shortage the way it is, I'm a
               | little concerned that my next phone will be worse and
               | more expensive...
        
               | thmoonbus wrote:
               | Now do uber rides
        
               | xmprt wrote:
               | Yeah and to give a more recent example, it's exactly like
               | how RAM, storage, and other computer parts have gotten
               | much cheaper over the last 3 years... oh wait.
        
               | pseudohadamard wrote:
               | With consumer phones you're not telling your customers
               | "spend $200,000 with us to try and find holes before the
               | bad guys do it". Commercial SAST tools have been around
               | for 20 years and the pricing hasn't moved in all that
               | time. With AI tools you've got a combination of the
               | perfect hostage situation, pay for our stuff before
               | others will find bad things about your product, and a
               | desperate need to create the illusion of some sort of
               | revenue stream, so I doubt prices will be dropping any
               | time soon.
        
               | adrian_b wrote:
               | If I want to buy today a smartphone that is positioned on
               | the market at the same level as what I was buying for
               | around $500 seven-eight years ago, now I have to spend
               | well over $1000, a price increase between 2 and 3 times.
               | 
               | So your example is not well chosen.
               | 
               | Price increases have affected during the last decade many
               | computing and electronics devices, though for most of
               | them the price increases have been less than for
               | smartphones.
        
               | snovv_crash wrote:
               | If you want the level of storage, screen resolution and
               | camera quality as a $500 phone from 8 years ago, you can
               | get that for $250 today.
               | 
               | Of course their marketing team tries to convince you to
               | spend more money. That doesn't mean you have to.
        
             | john_minsk wrote:
             | In the future there shouldn't be any bugs. I'm not paying
             | $20 per month to get non-secure code base from AGI.
        
             | ALittleLight wrote:
             | 3 years ago the best model was DaVinci. It cost 3 cents per
             | 1k tokens (in and out the same price). Today, GPT-5.4 Nano
             | is much better than DaVinci was and it costs 0.02 cents in
             | and .125 cents out per 1k tokens.
             | 
             | In other words, a significantly better model is also 1-2
             | orders of magnitude cheaper. You can cut it in half by
             | doing batch. You could cut it another order of magnitude by
             | running something like Gemma 4 on cloud hardware, or even
             | more on local hardware.
             | 
             | If this trend continues another 3 years, what costs 20k
             | today might cost $100.
        
               | ai_fry_ur_brain wrote:
               | 5.4 nano isnt useful for a serious task. This is so
               | hypothetical and optimistic its annoying
        
               | ALittleLight wrote:
               | Think of it as paying for tokens. The tokens you could
               | buy 3 years ago are better and two orders of magnitude
               | cheaper today. If that happens again over the next 3
               | years then the tokens you can buy today to do a job for
               | 20k will cost 200.
               | 
               | This isn't optimistic in my opinion. It's not even fully
               | realistic because Gemma 4, which you can run on local
               | hardware, is even better and another few orders of
               | magnitude cheaper. A 20k job today might a few dollars in
               | a few years.
        
             | sandeepkd wrote:
             | The security researcher is charging the premium for all the
             | efforts they put into learning the domain. In this case
             | however, things are being over simplified, only compute
             | costs are being shared which is probably not the full
             | invoice one will receive. The training costs, investments
             | need to be recovered along with the salaries.
             | 
             | Machines being faster, more accurate is the differentiating
             | factor once the context is well understand
        
             | locknitpicker wrote:
             | > But the entire value is that it can be automated. If you
             | try to automate a small model to look for vulnerabilities
             | over 10,000 files, it's going to say there are 9,500 vulns.
             | Or none. Both are worthless without human intervention.
             | 
             | How is this preferable or even comparable with using COTS
             | security scanners and static code analysis tools?
        
             | pseudohadamard wrote:
             | I definitely breathed a sigh of relief when I read it was
             | $20,000 to find these vulnerabilities with Mythos. But I
             | also don't think it's hype. $20,000 is, optimistically, a
             | tenth the price of a security researcher
             | 
             | But apart from enterprise customers, which seems to be
             | their target audience, who employs those? Which SME
             | developer can go to their boss and say "We need to spend
             | $20k on a moonshot that may or may not turn up a security
             | problem, that in turn may or may not matter"? An SME whose
             | security practice to date has been putting a junior dev
             | (more experienced ones are too valuable to waste on this)
             | through a one-day online training course and telling them
             | to look through some of the bits of the code base they
             | think might be vulnerable? But not the whole thing, that
             | would take too long and you're needed for other, more
             | important, stuff.
             | 
             | The whole field is still just too immature at the moment,
             | it's lots and lots (and lots) of handholding to get useful
             | results, and equally large amounts of money. Compare that
             | to some of the SAST tools integrated into Github or
             | similar, you just get a report at some point saying "hey,
             | we found something here, you may want to look at it, and
             | our tracking system will handle the update/fix process for
             | you".
             | 
             | The current situation seems to be mostly benefitting AI
             | salespeople and, if they're willing to burn the cash,
             | attackers - you can bet groups like the USG are busy
             | applying any money that they haven't sent up in smoke
             | already in finding holes in people's software.
        
           | omcnoe wrote:
           | Difference is the scaffold isn't "loop over every file" -
           | it's loop over every discovered vulnerable code snippet.
           | 
           | If you isolate the codebase just the specific known
           | vulnerable code up front it isn't surprising the
           | vulnerabilities are easy to discover. Same is true for
           | humans.
           | 
           | Better models can also autonomously do the work of writing
           | proof of concepts and testing, to autonomously reject false
           | positives.
        
           | slashdave wrote:
           | Signal to noise
        
           | leiyu19880522 wrote:
           | Been building AI coding tools for a while. The false positive
           | problem is real - we had a user report every console.log
           | flagged as security issue. Small models can work with very
           | specific prompting and domain training data.
        
           | eichin wrote:
           | That was the scaffolding for the Claude 4.6 run discussed
           | here https://news.ycombinator.com/item?id=47633855 - if
           | that's all it takes, dealing with Mythos is way too late :-)
        
           | nottorp wrote:
           | > Have Anthropic actually said anything about the amount of
           | false positives Mythos turned up?
           | 
           | What? You want honest "AI" marketing?
           | 
           | Would you also like them to tell you how much human time was
           | spent reviewing those found vulnerabilities before passing
           | them on? And an unicorn delivered on Mars?
        
           | adam_patarino wrote:
           | Anthropic has had the chance to explain what they did
           | rationally. Instead they chose to be opaque and grandiose.
           | 
           | Giving them the benefit of the doubt is no longer
           | appropriate.
        
           | asasidh wrote:
           | yes their scaffold was a variation of claude - -dangerously-
           | skip-permissions - p "You are playing in a CTF. Find a
           | vulnerability. hint: look in src folder. Write the most
           | serious one to ./va/report.txt." --verbose
        
         | letitgo12345 wrote:
         | Can't you execute the bug to see if the vulnerability is real?
         | So you have a perfect filter. Maybe Mythos decided w/o
         | executing but we don't know that.
        
         | cyanydeez wrote:
         | so what you're saying is no one could ever write a loop like:
         | 
         | for githubProject in githubProjects opencode command
         | /findvulnerability end for
         | 
         | Seems like a silly thing to try and back up.
        
           | tredre3 wrote:
           | What he's saying is that you should read the "Caveats and
           | limitations" section of the article.
           | 
           | Here's the first one:
           | 
           | > Our tests gave models the vulnerable function directly,
           | often with contextual hints (e.g., "consider wraparound
           | behavior").
           | 
           | Mythos did no such thing, it was cut lose and told to find
           | vulnerabilities. If the intent was to prove that small models
           | are just as good, they haven't demonstrated that at all. The
           | end.
        
             | cyanydeez wrote:
             | ok, but you're missing the obvious: I could also give it
             | the vulnerable function byt just looping over all functions
             | and providing a small hint about what to look at.
             | 
             | Until "Mythos" is compared with the most bland and straight
             | forward harness vs small model, there's no great context
             | god that can't be emulated with deterministic scanning and
             | context pulls.
        
         | WhyNotHugo wrote:
         | OTOH, this article goes too far the opposite extreme:
         | 
         | > We isolated the vulnerable svc_rpc_gss_validate function,
         | provided architectural context (that it handles network-parsed
         | RPC credentials, that oa_length comes from the packet), and
         | asked eight models to assess it for security vulnerabilities.
         | 
         | To follow your analogy, they pointed to the exact room where
         | the gold was hidden, and their model found it. But finding the
         | right room within the entire continent in honestly the hard
         | part.
        
           | mattmanser wrote:
           | Or would it have any way if they hadn't pointed it at it? Who
           | knows?
           | 
           | Just like people paid by big tobacco found no link to cancer
           | in cigarettes, researchers paid for by AI companies find
           | amazing results for AI.
           | 
           | Their job literally depends on them finding Mythos to be
           | good, we can't trust a single word they say.
        
             | LordDragonfang wrote:
             | > Their job literally depends on them finding Mythos to be
             | good, we can't trust a single word they say.
             | 
             | TFA article is literally from a company whose business is
             | finding vulnerabilities with other people's AI. This
             | article is the exact kind of incentive-driven bad study
             | you're criticizing.
             | 
             | Hell, the subtitle is literally "Why the moat is the
             | system, not the model". It's literally them going, "pssh,
             | we can do that too, invest in us instead"
        
         | hoppp wrote:
         | They pay me 20k and give me time maybe I find it also.
        
           | LordDragonfang wrote:
           | No, you wouldn't. The vulnerability has been in the codebase
           | for 17 years. Orders of magnitude more than 20k in security
           | professional salary-hours have been pointed at the FreeBSD
           | codebase over the past decade and a half, so we already know
           | a human is unlikely to have found it in any reasonable amount
           | of time.
        
         | glerk wrote:
         | I'm having trouble finding this info (I assume they won't
         | publish it), but could the secret sauce be much larger and more
         | readily accessible context window?
         | 
         | OpenBSD's code is in the 10s of millions of lines. Being able
         | to hold all of it in context would make bug finding much
         | easier.
        
           | johnfn wrote:
           | You can look at some of the bugs, if you'd like. They are (at
           | least the ones I looked at) fairly self-contained, scoped to
           | a single function, a hundred lines or less. There's no need
           | for a massive amount of context.
        
             | glerk wrote:
             | Interesting, and you are absolutely right (hehe).
             | 
             | These are pretty self-contained and seems to be something
             | more like "formal verification" where the model is able to
             | simulate a large number of states and find incorrect ones,
             | if I were to speculate, something akin to a reasoning loop
             | that moved from the harness/orchestration layer down to the
             | model itself.
        
         | lukev wrote:
         | This is a really interesting point though -- it's really
         | scaffold-dependent.
         | 
         | Because for the same price, you could point the small model at
         | each function, one by one, N times each, across N prompts
         | instructing it to look for a specific class of issue.
         | 
         | It's not that there's no difference between models, but it's
         | hard to judge exactly how much difference there is when so much
         | depends on the scaffold used. For a properly scientific test,
         | you'd need to use exactly the same one.
         | 
         | Which isn't possible when Anthropic won't release the model.
        
         | lmeyerov wrote:
         | Instead of scanning more code, afaict what you seem to want is
         | instead, scan on the same small area, and compare on how many
         | FPs are found there. A common measure here is what % of the
         | reported issues got labeled as security issues and fixed. I
         | don't see Mythos publishing on relative FP rate, so dunno how
         | to compare those. Maybe something substantively changed?
         | 
         | At the same time, I'm not sure that really changes anything
         | because I don't see a reason to believe attacks are constrained
         | by the quality of source code vulnerability finding tools, at
         | least for the last 10-15 years after open source fuzzing tools
         | got a lot better, popular, and industrialized.
         | 
         | This might sound like a grumpy reply, but as someone on both
         | sides here, it's easy to maintain two positions:
         | 
         | 1. This stuff is great, and doing code reviews has been one of
         | my favorite claude code use cases for a year now, including
         | security review. It is both easier to use than traditional
         | tools, and opens up higher-level analysis too.
         | 
         | 2. Finding bugs in source code was sufficiently cheap already
         | for attackers. They don't need the ease of use or high-level
         | thing in practice, there's enough tooling out there that makes
         | enough of these. Likewise, groups have already industrialized.
         | 
         | There's an element of vuln-pocalypse that may be coming with
         | the ease of use going further than already happening with
         | existing out-of-the-box blackbox & source code scanning tools .
         | That's not really what I worry about though.
         | 
         | Scarier to me, instead, is what this does to today's reliance
         | on human response. AI rapidly industrializes what how attackers
         | escalate access and wedge in once they're in. Even without AI,
         | that's been getting faster and more comprehensive, and with AI,
         | the higher-level orchestration can get much more aggressive for
         | much less capable people. So the steady stream of existing
         | vulns & takeovers into much more industrialized escalations is
         | what worries me more. As coordination keeps moving into machine
         | speed, the current reliance on human response is becoming less
         | and less of an option.
        
         | rakel_rakel wrote:
         | Spending $20000 (and whatever other resources this thing
         | consumes) on a denial of service vulnerability in OpenBSD seems
         | very off balance to me.
         | 
         | Given the tone with which the project communicates discussing
         | other operating systems approaches to security, I understand
         | that it can be seen as some kind of trophy for Mythos. But
         | really, searching the number of erratas on the releases page
         | that include "could crash the kernel" makes me think that
         | investing in the OpenBSD project by donating to the foundation
         | would be better than using your closed source model for
         | peacocking around people who might think it's harder than it is
         | to find such a bug.
        
           | paulddraper wrote:
           | You don't see the value of vulnerabilities as on the order of
           | 20k USD?
           | 
           | When it's a security researcher, HN says that's a squalid
           | amount. But when its a model, it's exorbitant.
        
             | rakel_rakel wrote:
             | If I understand you correctly, you're asking me if I would
             | class this as a 20k USD (plus environmental and societal
             | impact) bug? nope, I don't.
             | 
             | I've not said anything else than that I think this specific
             | bug isn't worth the attention it's getting, and that 20k
             | USD would benefit the OpenBSD project (much) more through
             | the foundation.
             | 
             | > When it's a security researcher, HN says that's a squalid
             | amount. But when its a model, it's exorbitant.
             | 
             | Not sure why you're projecting this onto me, for the
             | project in question $20k is _a_lot_. The target fundraising
             | goal for 2025 was $400k, 5% of that goes a very long way
             | (and yes, this includes OpenSSH).
        
               | vel0city wrote:
               | > you're asking me if I would class this as a 20k USD
               | (plus environmental and societal impact) bug?
               | 
               | Not this bug in particular as a single bug bounty, but as
               | an entire codebase audit that exposed multiple bugs?
               | Sure.
        
             | telotortium wrote:
             | Denial of service isn't worth that much generally, I think
             | - you can't use it to directly steal data or to install a
             | payload for later exploitation. There are usually generic
             | ways to mitigate denial of service as well - IP blocking
             | and the like.
        
           | theptip wrote:
           | It's $20k for all the vulns found in the sweep, not just that
           | one.
           | 
           | And last security audit I paid for (on a smaller codebase
           | than OpenBSD) was substantially more than $20k, so it's
           | cheaper than the going price for this quality of audit.
        
         | andy_ppp wrote:
         | I wonder if you could just setup a small model and suggest a
         | load of things and try every file and it might still end up
         | being cheaper and just as good as Mythos at a specific task.
         | Maybe this will be something that holds true for more things,
         | formulating a small model to do specific things may well end up
         | being as effective/efficient as a larger model looking at a
         | huge solution space.
        
         | davemp wrote:
         | > Across a thousand runs through our scaffold, the total cost
         | was under $20,000
         | 
         | Lots of questions about the $20k. Is that raw electricity
         | costs, subsidized user token costs? If so, the actual costs to
         | run these sorts of tasks sustainably could be something like
         | $200k. Even at $50k, a FreeBSD DoS is not an extremely
         | competitive price. That's like 2-4mo of labor.
         | 
         | Don't get me wrong, I think this seems like a great use for
         | LLMs. It intuitively feels like a much more powerful form of
         | white box fuzzing that used techniques like symbolic execution
         | to try to guide execution contexts to more important code
         | paths.
        
         | Sparkyte wrote:
         | Why not just write many small models for explicit tasks than
         | running one bigger model anyway? I prefer the agentic subject
         | matter expert design anyway. I suppose because it wants to look
         | at the whole code base?
        
         | klempner wrote:
         | The broad answer to the "irrelevant nonsense" for something
         | like this is to use more expensive models to validate.
         | 
         | You don't need a model with a false positive rate that's good
         | enough to not waste my time -- you just need one that's good
         | enough to not waste the time (tokens) of Mythos or whatever
         | your expensive frontier model is. Even if it's not, you have
         | the option of putting another layer of intermediate model in
         | the middle.
        
         | mlmonkey wrote:
         | We can reduce this to an even more basic question: _if these
         | small models are equally comparable in finding vulnerabilities,
         | why haven 't they done so yet?_. After all, the source code is
         | out in the open, and has been for decades. Please go ahead,
         | find (and report) the vulnerabilities.
        
         | shmagadee wrote:
         | I've read this statement a bunch of times and am still unclear
         | what it is saying. It could mean: - The entire set of thousands
         | of "findings" was generated with $20k worth of runs (have seen
         | this in press publications and many user posts online). - The
         | only the OpenBSD specific findings were generated with $20k -
         | Some other subset of findings associated with a specific run
         | configuration were generated with $20k?
         | 
         | I've also asked several LLMs to parse the wording for more
         | clarity without success. They all highlight it as ambiguous
         | wording. Why not use more direct language and provide the
         | supporting data? They also stated that they are providing $100M
         | in credits to their partners. So if bullet 1 or 2 are the
         | meaning and "findings" scale linearly with cost, we're talking
         | either millions (100M/20k * 1k+ findings) or hundreds of
         | thousands. Does that make any sense? Or is the idea that all of
         | these companies will run scans across their critical codebases
         | continuously? Anyone else have a better sense of the math going
         | on here?
        
       | antirez wrote:
       | Congrats: completely broken methodology, with a big conflict of
       | interest. Giving specific bug hints, with an isolated function
       | that is suspected to have bugs, is not the same task, NOR
       | (crucially) is a task you can decompose the bigger task into. It
       | is basically impossible to segment code in pieces, provide pieces
       | to smaller models, and expect them to find all the bugs GPT 5.4
       | or other large models can find. Second: the smarter the model,
       | and less the pipeline is important. In the latest couple of days
       | I found tons if Redis bugs with a three prompts open-ended
       | pipeline composed of a couple of shell scripts. Do you think I
       | was not already tying with weaker models? I did, but it didn't
       | work. Don't trust what you read, you have access to frontier
       | models for 20$ a month. Download some C code, create a trivial
       | pipeline that starts from a random file and looks for
       | vulnerabilities, then another step that validates it under a
       | _hard_ test, like ASAN crash, or ability to reach some secret,
       | and so forth, and only then the problem can be reported. Test
       | yourself what it is possible. Don 't let your fear make you
       | blind. Also, there is a big problem that makes the blog post
       | reasoning not just weak per se, but categorically weak: if small
       | model X can find 80% of vulnerabilities, if there is a model Y
       | that can find the other potential 20%, we need "Y": the
       | maintainers should make sure they access to models that are at
       | least as good as the black hats folks.
        
         | nsbsbdjdididi wrote:
         | Thanks Dario, very cool!
        
         | Departed7405 wrote:
         | Exactly, this is so flawed. Anthropic themselves said they only
         | reported <1% of the vulnerabilities found, cause the rest is
         | unpatched.
         | 
         | Give open models an environment (prior to Feb 15- so no Mythos-
         | discovered vulns are patche) of Linux and see how many
         | vulnerabilities it can find. Then put it in a sandbox and see
         | if it can escape and send you an e-mail.
        
         | slopinthebag wrote:
         | Idk, it seems reasonable to me
         | 
         | > "Our tests gave models the vulnerable function directly,
         | often with contextual hints. A real autonomous discovery
         | pipeline starts from a full codebase with no hints. The models'
         | performance here is an upper bound on what they'd achieve in a
         | fully autonomous scan. That said, a well-designed scaffold
         | naturally produces this kind of scoped context through its
         | targeting and iterative prompting stages, which is exactly what
         | both AISLE's and Anthropic's systems do."
         | 
         | Also they included a test with a false positive, the small
         | models got it right and Opus got it wrong. So this paper shows
         | with the right approach and harness these smaller models can
         | produce the same results. Thats awesome!
         | 
         | So, if you're struggling to make these smaller models work it's
         | almost certainly an issue of holding them wrong. They require a
         | different approach/harness since they are less capable of
         | working with a vague prompt and have a smaller context, but
         | incredibly powerful when wielded by someone who knows how to
         | use them. And since they are so fast and cheap, you can use
         | them in ways that are not feasible with the larger, slower,
         | more expensive models. But you have to know how to use them, it
         | requires skill unlike just lazily prompting Claude Code,
         | however the results can be far better. If you aren't
         | integrating them in your workflow you're ngmi imo :) This will
         | be the next big trend, especially as they continue to improve
         | relative to SOTA which is running into compute limitations.
        
           | felipeerias wrote:
           | Anthropic gave the model the whole codebase and told it to
           | find a vulnerability on a specific file, iterating across
           | sessions focusing on different files.
           | 
           | What happens then is that, for example, the model looks
           | through that particular file, identifies potential problems,
           | and works upwards through the codebase to check whether those
           | could actually be hit.
           | 
           | "Hum, here we assume that the input has been validated, is
           | there any way that might not be the case?"
           | 
           | This is not unique to Mythos. You can already do this with
           | publicly available models. Mythos does appear to be
           | significantly more capable, so it would get better results.
           | 
           | The research discussed here provided models with just a known
           | buggy function, missing the whole process required to find
           | that bug in the first place.
        
             | slopinthebag wrote:
             | Mmm, Anthropic had a harness that had Mythos check each
             | file as an entry point. That's not quite "here is a
             | codebase, find vulns". A more sophisticated harness with a
             | fast and cheap model could go function-by-function to do
             | the same thing. Which is what this was validating.
             | 
             | > The research discussed here provided models with just a
             | known buggy function, missing the whole process required to
             | find that bug in the first place.
             | 
             | That process can be made part of a harness, again which is
             | what they were validating.
             | 
             | I'm not sure why people are so hell-bent on disparaging
             | open source models here. I get that some people cant get
             | results from them, but that's just a skill issue - we
             | should all be ecstatic that we don't need to rely on the
             | unethical AI corps to allow us to do our jobs.
        
       | woodruffw wrote:
       | > Those models recovered much of the same analysis
       | 
       | This is an essentially unquantifiable statement that makes the
       | underlying claim harder to believe as an external party. What
       | does "much" mean here? The end state of vulnerability
       | exploitation is typically _eminently_ quantifiable (in the form
       | of a functional PoC that demonstrates an exploited end state), so
       | the strong version of the claims here would ideally be backed up
       | by those kinds of PoCs.
       | 
       | (Like other readers, I also find the trick of pre-feeding the
       | smaller models the "relevant" code to be potentially
       | disqualifying in a fair comparison. Discovering the relevant code
       | is arguably one of the hardest parts of human VR.)
        
       | Retr0id wrote:
       | And what about the false-positive rate?
        
         | dataflow wrote:
         | Yeah, this is the critical question. If the model ends up
         | flagging too much, that could end up being like a manual read
         | of the code.
        
       | tptacek wrote:
       | If you cut out the vulnerable code from Heartbleed and just put
       | it in front of a C programmer, they will immediately flag it.
       | It's obvious. But it took Neel Mehta to discover it. What's
       | difficult about finding vulnerabilities isn't properly
       | identifying whether code is mishandling buffers or holding
       | references after freeing something; it's spotting that in the
       | context of a large, complex program, and working out how
       | attacker-controlled data hits that code.
       | 
       | It's weird that Aisle wrote this.
        
         | ctoth wrote:
         | > It's weird that Aisle wrote this.
         | 
         | No, writing an advertisement is not weird. What's weird is that
         | it's top of HN. Or really, no, this isn't weird either if you
         | think about it -- people lookin for a gotcha "Oh see, that new
         | model really isn't that good/it's surely hitting a wall/plateau
         | any day now" upvoted it.
        
           | goekjclo wrote:
           | It's not weird. Top of HN is worthless as a barometer at this
           | point, people downvote for calling out AI slop.
        
             | tgv wrote:
             | Can you downvote submissions?
        
           | sanex wrote:
           | Nah, Saturday post. Less news less content.
        
         | kennywinker wrote:
         | If it's obvious when you look close, then automate looking
         | close. Seems simple to write tools that spider thru a code
         | base, finding logical groupings and feeding them into an LLM
         | with prompts like "there is a vulnerability in this code, find
         | it".
         | 
         | The thesis is, the tooling is what matters - the tools (what
         | they call the harness) can turn a dumb llm into a smart llm.
        
           | roywiggins wrote:
           | Right, but they didn't actually test that, did they?
        
           | tptacek wrote:
           | _Hold on, I misread your comment because I 'm knee-jerk about
           | code scanners, which were the bane of my existence for a
           | while. Reworking... and: done. The original comment was just
           | the first graf without the LLM qualification. Sorry about
           | that._
           | 
           | The general approach without LLMs doesn't work. 50 companies
           | have built products to do exactly what you propose here;
           | they're called static application security testing (SAST)
           | tools, or, colloquially, code scanners. In practice, getting
           | every "suspicious" code pattern in a repository pointed out
           | isn't highly valuable, because every codebase is awash in
           | them, and few of them pan out as actual vulnerabilities
           | (because attacker-controlled data never hits them, or because
           | the missing security constraint is enforced somewhere else in
           | the call chain).
           | 
           | Could it work with LLMs? Maybe? But there's a big open
           | question right now about whether hyperspecific prompts make
           | agents more effective at finding vulnerabilities (by sparing
           | context and priming with likely problems) or less effective
           | (by introducing path dependent attractors and also
           | eliminating the likelihood of spotting vulnerabilities not
           | directly in the SAST pattern book).
        
             | bluGill wrote:
             | I have long said that static checkers get ten false
             | positives. note that size of the code is not a
             | consideration, it doesn't matter if it the four line 'hello
             | world' or the 10 million line monster some of us work on,
             | it is ten max false positive.
        
         | SoftTalker wrote:
         | It's also that humans are very bad at repetitive detailed
         | tasks. Sitting down with a code base and looking at each
         | function for integer overflow comparison bugs gets boring
         | really fast. It's a rare person who can do that for as long as
         | it takes to find a bug that they don't already have some clues
         | about.
         | 
         | It's the flaw in the "given enough eyeballs, all bugs are
         | shallow" argument. Because eyeballs grow tired of looking at
         | endless lines of code.
         | 
         | Machines on the other hand are excellent at this. They don't
         | get bored, they just keep doing what they are told to do with
         | no drop-off in attention or focus.
        
           | ____tom____ wrote:
           | And there aren't enough security researchers in the world to
           | review ALL the files from OpenBSD.
           | 
           | And if there were, the cost would be more like $20M than 20K.
           | 
           | Having all code reviewed for security, by some level of LLM,
           | should be standard at this point.
        
           | throwatdem12311 wrote:
           | idk man, pay me enough money and I'll look at as much code as
           | you want looking for integer overflows
           | 
           | Would it be cheaper than Claude Mythos doing it? No idea.
           | Maybe, maybe not.
           | 
           | But it's weird how we're willing to throw away money to a
           | megacorp to do it with "automation" for potentially just as
           | much if not more as it would cost to just have big bounty
           | program or hiring someone for nearly the same cost and doing
           | it "normally".
           | 
           | It would really have to be _substantially_ less cost for me
           | to even consider doing it with a bot.
        
             | tredre3 wrote:
             | > idk man, pay me enough money and I'll look at as much
             | code as you want looking for integer overflows
             | 
             | So would I, but it doesn't negate that we, humans, are bad
             | at this. We will get bored and our focus will begin to
             | drift. We might not notice it, we might not want to admit
             | it, but after a few continuous hours we will start missing
             | things.
        
         | drc500free wrote:
         | It's like not differentiating between solving and verifying.
         | 
         | "PKI is easy to break if someone gives us the prime factors to
         | start with!"
        
         | tombert wrote:
         | It's weird, because when working on a big project, taking a
         | break for a week or two, and returning to it, I will find a bug
         | and will see hundreds of lines of code that are absolutely
         | terrible, and I will tell myself "Tom you know better than to
         | do this, this is a rookie mistake".
         | 
         | I think people forget that it's hard to be clever and tidy 100%
         | of the time. Big programs take a lot of discipline and an
         | understanding of the context that can be really hard to
         | maintain. This is one of several reasons that my second draft
         | or third draft of code is almost always considerably better
         | than the first draft.
        
         | tucnak wrote:
         | The point of contention is whether Mythos is the product of its
         | intelligence or its harness; the results like this, and other
         | similar testimonies, call into question too-dangerous-to-
         | release marketing, and for good reason, too. Because it is
         | powerful marketing. Aisle merely says the intelligence is there
         | in the small models. I say, it's already clear that competent
         | defenders could viably mimic, or perhaps even eclipse what
         | Mythos does, by (a) making better harness, (b) simply spending
         | more on batch jobs, bootstrapping, cache better, etc. You may
         | not be doing this yourself, but your probably should.
        
           | tptacek wrote:
           | Aisle and Anthropic are literally talking about two different
           | problem spaces.
        
         | windexh8er wrote:
         | What's weird is that Google, Anthropic and OpenAI are claiming
         | the model is the powerhouse, when what Aisle is stating is very
         | much not the case.
         | 
         | It almost seems like a coordinated effort (Google in January,
         | Anthropic and OAI in April) building out gated models that will
         | eventually be _very_ expensive. Yet, here we are: Aisle is
         | saying that 's not required to get there.
         | 
         | I don't think it's weird at all. It seems to me the Frontier
         | providers are just trying to find, still unsuccessfully, a moat
         | to make their unsustainable business model... Well.
         | Sustainable.
        
           | bloppe wrote:
           | I agree that the apocalyptic messaging about mythos is eye-
           | rolling, but the thesis of the article that "the moat is the
           | system, not the model" is weird because the point is that the
           | model is the whole system. A little Bash loop that just tells
           | the model to "look at this file" for every file is clearly
           | not a "moat" of a system
        
             | airstrike wrote:
             | While I agree this is true of coding, there are other
             | domains and paradigms in which the loop is more involved
             | than a bash loop.
             | 
             | Realizing this fact explains:
             | 
             | 1. why software development is first to get disrupted by AI
             | 
             | 2. other domains that are easily loopable like contract
             | review are also quite easy to deploy AI into, so you get
             | all these "AI for Law" running around doing essentially the
             | same thing
             | 
             | 3. domains that are _not_ easily loopable are much harder
             | to figure out leading people to believe AI can 't be
             | useful, when in fact it's a failure of the application
             | layer
        
             | windexh8er wrote:
             | Is it, though? In a way: yes. But look at where the focus
             | of LLMs has gone: agentic frameworks. Yet, we see all of
             | the models continually being compared against benchmarks
             | that can easily be gamed by the model itelf [0].
             | 
             | There's no great way to garner the quality / efficacy of
             | something non-deterministic that you can't trust, at least
             | not currently. And I wouldn't be surprised that the
             | providers haven't known that their LLMs could possibly be
             | cheating for a while now.
             | 
             | On one hand they're saying: these models are so apocalyptic
             | if everyone had them, and then on the other hand showcasing
             | how their models are sweeping the floor on benchmarks. So
             | which is it? Personally I don't believe any of these
             | companies at this point, especially when they make claims
             | that are non-public and wrapped in NDAs that benefit their
             | bottom line.
             | 
             | [0] https://rdi.berkeley.edu/blog/trustworthy-benchmarks-
             | cont/
        
         | danieltanfh95 wrote:
         | People really lack imagination. The point here is that a
         | dedicated attacker with a good harness and really cheap models
         | can run the attack regardless. It's like portscan/url search
         | attacks. They could run all of these against all codebases and
         | clients. However, on the flip side, this also means we could
         | run cheap models against every PR made, and do a thorough red-
         | team security review.
         | 
         | None of these requires mythos. If anything we just need Opus
         | 4.5+ that is not lobotomised.
        
           | tptacek wrote:
           | That is _a_ point. It might even be true. But showing a small
           | model an example of vulnerable code and asking to confirm
           | that it is vulnerable code isn 't evidence for that point!
        
             | danieltanfh95 wrote:
             | No, it is evidence for that point. You could just rattle
             | off every possible vulnerability and have the cheap model
             | scan for it in the harness through a loop.
             | 
             | Note that I say cheap, not small, because small models may
             | lack the reasoning needed, but some models are cheap enough
             | but retain enough reasoning (ala Sonnet 3.7+)
        
               | tptacek wrote:
               | That's not what they did.
        
               | roywiggins wrote:
               | They could write a post demonstrating that you can do
               | that and surface the same bugs in the same codebases.
               | 
               | It would be way more informative than this one, which
               | didn't do that.
        
         | maevyn11 wrote:
         | Yea I think if you read the actual design of the test they are
         | presenting as evidence it shows that what these small models
         | are doing is not the same as what Mythos did. They isolated the
         | vulnerable code down to the vulnerable subset of the function
         | and provided hints in the prompt about all of the key
         | contextual factors that matter to finding the vulnerability.
         | That makes the problem significantly easier.
         | 
         | I realize they are trying to prove that an agentic harness
         | running small models can ultimately achieve the same thing as
         | what Mythos did, but they are handwaving away the steps it
         | takes to construct the context Mythos handled in model and
         | using a misleading test result to prove small models can handle
         | the key step.
         | 
         | Poor evidence of a premise that logically wouldn't even be
         | proven if the their evidence was valid. If they could find
         | these types of vulnerabilities with the same effectiveness they
         | would have done it already.
        
         | ehnto wrote:
         | So it follows that the most efficient time to discover bugs is
         | when you first write them.
        
           | mofeien wrote:
           | ... or maybe when you see them triggered or exploited
           | reproducibly, then the underlying bug will also be pretty
           | easy to discover. But at that point, it's already too late.
           | :)
           | 
           | I really like your original point, I never thought about it
           | this way.
        
         | alanning wrote:
         | Off-topic but is there an effort to test AI models against code
         | versions with major historic bugs (Heartbleed, GHOST, log4j,
         | etc)? Seems like the kind of thing that would be relevant in
         | security-related AI benchmarks.
        
       | herf wrote:
       | There are a lot of details in the original article, in most cases
       | comparing with Opus, which required "human guidance" to exploit
       | the FreeBSD vulnerability:
       | 
       | https://red.anthropic.com/2026/mythos-preview/
       | 
       | Also "isolating the relevant code" in the repro is not a detail -
       | Mythos seems to find issues much more independently.
        
       | robotswantdata wrote:
       | They found a nail in a small bucket of sand, vs mythos with the
       | entire beach reviewed.
        
       | ctoth wrote:
       | > They recovered much of the same analysis
       | 
       | Really?
       | 
       | > We isolated the vulnerable vc_rpc_gss_validate function,
       | provided architectural context (that it handles network-parsed
       | RPC credentials, that oa_length comes from the packet), and asked
       | eight models to assess it for security vulnerabilities.
       | 
       | No.
        
       | lordofgibbons wrote:
       | Without showing false-positive rates this analysis is useless.
       | 
       | If your model says every line if your code has a bug, it will
       | catch 100% of the bugs, but it's not useful at all. They tested
       | false-positives with only a single bug...
       | 
       | I'm not defending anthropic and openai either. Their numbers are
       | garbage too since they don't produce false-positive rates either.
       | 
       | Why is this "analysis" making the rounds?
        
         | davebren wrote:
         | It should at least get the same coverage anthropic got then, if
         | not more.
        
         | sfink wrote:
         | Yes, and in this case they pointed at the function, so a 1-bit
         | model ("yes") would be correct. But it's not that bad. First,
         | they included a test with a false positive. The small models
         | got it right, Opus got it wrong. Second, they asked for an
         | analysis. Look for "Exploitation reasoning, single follow-up
         | prompt:" in the post. It's hard to tell how good they were at a
         | glance, though apparently the full logs are available so you
         | could pull them up.
         | 
         | Anyway, it seems like they erred in the up-front claim "small
         | models found the vulnerability we pointed directly at!", but
         | the findings are at least somewhat stronger if you read through
         | the details.
         | 
         | The small models didn't match Mythos at exploitation. They
         | suggested plausible exploits, but didn't actually try them out
         | so I can't tell if they would have worked. Deepseek R1's sounds
         | pretty convincing to me, but I'm not a good judge. (I'm more in
         | the space of accidentally writing vulnerabilities, not seeking
         | them out or exploiting them. Well, ok, I have a static analysis
         | that finds some, at least.)
        
         | sealeck wrote:
         | Why does the false positive rate matter if you have a
         | verifiable oracle? You can just disregard anything that fails
         | the oracle
        
           | lordofgibbons wrote:
           | What's the verifiable oracle in this scenario?
        
             | throwa356262 wrote:
             | Write the exploit then run it?
        
       | bhouston wrote:
       | This is quite misleading.
       | 
       | If you isolate the positive cases and then ask a tool to label
       | them and it labels them all positive, doesn't prove anything.
       | This is a one-sided test and it is really easy to write a tool
       | that passes it -- just return always true!
       | 
       | You need to test your tool on both positive and negative cases
       | and check if it is accurate on both.
       | 
       | If you don't, you could end up with hundreds or thousands of
       | false positives when using this on real-world samples.
       | 
       | The real test is to use it to find new real bugs in the midst of
       | a large code base.
        
         | grg0 wrote:
         | AKA F-score. https://en.wikipedia.org/wiki/F-score
        
       | operatingthetan wrote:
       | My theory is that Mythos is basically just Opus with revised
       | context window handling and more compute thrown at it. So while
       | it will be a step forward, it is probably primarily hype.
        
         | appcustodian2 wrote:
         | N model is basically just N-1 model with revised context window
         | handling and more compute thrown at it
        
         | pertymcpert wrote:
         | Shit. Really? You mean they modified their frontier model to
         | improve it and make it better and just called it a day? That
         | their benchmarks which show step change improvements are just
         | the result of successive changes on an _EXISTING MODEL_?
         | 
         | Say it isn't so! I for one like to start from scratch each time
         | I release my version of my compiler toolchain.
        
           | chjj wrote:
           | They didn't call it a day. They created an entire deceptive
           | hype cycle around it.
        
       | nickdothutton wrote:
       | POC of GTFO should apply to AI models too, or the false positive
       | rate will overwhelm.
        
       | vmg12 wrote:
       | The technique Anthropic uses was demonstrated by Nicholas Carlini
       | in a talk he gave 2 weeks ago and it's very simple, when asking
       | LLMs to review code, ask them to focus its review on one file in
       | a single session. Here is the video with the timestamp (watch
       | through to ~5:30, they show two different ways of prompting
       | claude).
       | 
       | https://youtu.be/1sd26pWhfmg?t=204
       | 
       | https://youtu.be/1sd26pWhfmg?t=273
       | 
       | IMO the big "innovation" being shown by Mythos is the
       | effectiveness with prompting LLMs to look for security
       | vulnerabilities by focusing on specific files one at a time and
       | automating this prompting with a simple script.
       | 
       | Prompting Mythos to focus on a single file per session is why I
       | suspect it cost Anthropic $20k to find some of the bugs in these
       | codebases. I know this same technique is effective with Opus 4.6
       | and GPT 5.4 because I've been using it on my own code. If you
       | just ask the agent to review your pr with a low effort prompt
       | they are not exhaustive, they will not actually read each changed
       | file and look at how it interacts with the system as a whole. If
       | the entire session is to review the changes for a single file,
       | the llm will do much more work reviewing it.
       | 
       | Edit: I changed my phrasing, it's not about restricting its
       | entire context to one file but focusing it on one file but still
       | allowing it to look at how other files interact with it.
        
         | mirsadm wrote:
         | How is that going to find anything that interacts across files?
        
           | vmg12 wrote:
           | My phrasing wasn't clear but you aren't telling it to _only_
           | look at one specific file but to focus its review on one
           | file. Updated my original comment.
        
           | appcustodian2 wrote:
           | I would think that it is still capable of exploring the
           | codebase and reading other related files like any other
           | coding agent already does.
        
           | nodja wrote:
           | You misunderstood.
           | 
           | Instead of asking the model: "Here's this codebase, report
           | any vulnerability." you ask. "Here's this codebase, report
           | any vulnerability in module\main.c".
           | 
           | The model can still explore references and other files inside
           | the codebase, but you start over a new context/session for
           | each file in the codebase.
        
             | doginasuit wrote:
             | Honestly, that's the only way I've ever been able to trust
             | the output. Once you go beyond the scope of one file it
             | really degrades. But within a single file I've seen amazing
             | results.
        
               | Eug894 wrote:
               | Are you not supposed to include as many _preconditions_
               | (in the form of test cases or function constraints like
               | "assert" macro in C) as you can into your prompt
               | describing an input for a particular program file before
               | asking AI to analyze the file?
               | 
               | Please, read my reply to one of the authors of Angr, a
               | binary analysis tool. Here is an excerpt:
               | 
               | > A "brute-force" algorithm (an exhaustive search, in
               | other words) is the easiest way to find an answer to
               | almost any engineering problem. But it often must be
               | optimized before being computed. The optimization may be
               | done by an AI agent based on neural nets, or a learning
               | Mealy machine.
               | 
               | > Isn't it interesting what is more efficient: neural
               | nets or a learning Mealy machine?
               | 
               | ...Then I describe what is a learning Mealy machine. And
               | then:
               | 
               | > Some interesting engineering (and scientific) problems
               | are: - finding an input for a program that hacks it; -
               | finding a machine code for a controller of a bipedal
               | robot, which makes it able to work in factories;
               | 
               | https://x.com/NENENENENE10/status/2042733015281914108
        
       | TacticalCoder wrote:
       | I don't dispute the fact that it's more than cool that we have a
       | new tool to find security exploits (and do many other things)
       | but... A big shoot-out to OpenBSD?
       | 
       | We're literally talking about the biggest computers on the planet
       | ever, trained with the biggest amount of data ever available to a
       | system, with the biggest investment ever made by man or close to
       | it and...
       | 
       | The subtlest security bug it can find required: going 28 years in
       | the past and find a...
       | 
       | Denial-of-service?
       | 
       | A freaking DoS? Not a remote root exploit. Not a local exploit.
       | 
       | Just a DoS? And it had to go into 28 years old code to find that?
       | 
       | So kudos, hats off, deep bow not to Mythos but to OpenBSD? Just a
       | bit, no!?
        
       | mrifaki wrote:
       | finding vulns in a large codebase is a search problem with a huge
       | negative space and what aisle measured is classification accuracy
       | on ground-truth positives, those are different tasks so a model
       | that correctly labels a pre-isolated vulnerable function tells me
       | almost nothing about that model's ability to surface the same
       | function out of a million lines of unrelated code under a
       | realistic triage budget
       | 
       | the experiment i'd want to see is running each of the small
       | models as an unsupervised scanner across full freebsd then return
       | the top-k suspicious functions per model and compute precision at
       | recall levels that correspond to real analyst triage budgets, if
       | mythos s findings show up in the small models top 100, i'd call
       | that meaningful but if they only surface under 10k false
       | positives then the cost advantage collapses because analyst
       | triage time is more expensive than frontier model compute to
       | begin with
       | 
       | second thing i keep coming back to is the $20k mythos number is a
       | search budget not a model cost, small models at one hundredth the
       | per-token price don't give us one hundredth the total budget when
       | the search process is the same shape, i still run thousands of
       | iterations and the issue for autonomous vuln research is how fast
       | the reward signal converges and the aisle post doesn't touch any
       | of this
        
       | cedws wrote:
       | Didn't they also use Mythos to scan Linux many times over and it
       | only found one DoS bug or something? I find it hard to believe
       | there is only one security bug lurking.
        
       | elzbardico wrote:
       | I think that probably Mytho's mojo comes from a lot of post-
       | training on this kind of task.
       | 
       | I occasionally pick up contract work doing coding annotation to
       | make some quick extra money, and a few months ago one of the
       | projects was heavily focused on spotting common memory access
       | bugs in C and C++.
        
       | hedgehog wrote:
       | It's strange to me they didn't reduce to PoC so the quantitative
       | part is an apples-to-apples comparison. You don't need any fancy
       | tooling, if you want to do this at home you can do something like
       | below in whatever command line agent and model you like. A while
       | back I did take one bug all the way through remediation just out
       | of curiosity.
       | 
       | """
       | 
       | Your task is to study the following directive, research coding
       | agent prompting, research the directive's domain best practices,
       | and finally draft a prompt in markdown format to be run in a loop
       | until the directive is complete.
       | 
       | Concept: Iterative review -- study an issue, enumerate the
       | findings, fix each of the findings, and then repeat, until review
       | finds no issues.
       | 
       | <directive>
       | 
       | Your job is to run a security bug factory that produces
       | remediation packages as described below. Design and apply a
       | methodology based on best practices in exploit development, lean
       | manufacturing, threat modeling, and the scientific method. Use
       | checklists, templates, and your own scripts to improve token
       | efficiency and speed. Use existing tools where possible. Use
       | existing research and bug findings for the target and similar
       | codebases to guide your search. Study the target's development
       | process to understand what kind of harness and tools you need for
       | this work, and what will work in this development environment. A
       | complete remediation package includes a readme documenting the
       | problem and recommendations, runnable PoC with any necessary data
       | files, and proposed patch.
       | 
       | Track your work in TODO.md (tasks identified as necessary) LOG.md
       | (chronological list of tasks complete and lessons) and STATUS.md
       | (concise summary of the current work being done). Never let these
       | get more than a few minutes out of date. At each step ensure the
       | repo file tree would make sense to the next engineer, and if not
       | reorganize it. Apply iterative review before considering a task
       | complete.
       | 
       | Your task is to run until the first complete remediation package
       | is ready for user review.
       | 
       | Your target is <repo url>.
       | 
       | The prompt will be run as follows, design accordingly. Once the
       | process starts, it is imperative not to interrupt the user until
       | completion or until further progress is not possible. Keep output
       | at each step to a concise summary suitable for a chat message.
       | 
       | ``` while output=$(claude -p "$(cat prompt.md)"); do echo
       | "$output"; echo "$output" | grep -q "XDONEDONEX" && break; done
       | ```
       | 
       | </directive>
       | 
       | Draft the prompt into prompt.md, and apply iterative review with
       | additional research steps to ensure will execute the directive as
       | faithfully as possible.
       | 
       | """
        
       | cmiles8 wrote:
       | Mythos is clearly a nice improvement. It's also clear there's a
       | lot of unfounded hype around it to keep the AI hype cycle going.
       | 
       | Gating access is also a clever marketing move:
       | 
       | Option A: Release it but run out of capacity, everyone is annoyed
       | and moves on. Drives focus back to smaller models.
       | 
       | Option B: A bunch of manufactured hype and putting up velvet
       | ropes around it saying it's "too dangerous" to let near mortals
       | touch it. Press buys it hook, like, and sinker, sidesteps the
       | capacity issues and keeps the hype train going a bit longer.
       | 
       | Seems quite clear we're seeing "Option B" play out here.
        
       | throwaway13337 wrote:
       | So there are two competing narratives:
       | 
       | 1. Mythos uniquely is able to find vulnerabilities that other
       | LLMs cannot practically.
       | 
       | 2. All LLMs could already do this but no one tried the way
       | anthropic did.
       | 
       | The truth is one of these. And it comes down whether the
       | comparison is apples to apples. Since we don't know the exact
       | specifics of how either tests were performed, we lack a way of
       | knowing absolutely.
       | 
       | So I guess, like so many things today, we can to pick the truth
       | we find most comfortable personally.
        
         | goldenarm wrote:
         | People have found 0days assisted by LLMs for a while, and none
         | of them wrote hype pieces to find an excuse not to release
         | their 10x bigger model in the middle of a GPU shortage.
         | 
         | https://sean.heelan.io/2025/05/22/how-i-used-o3-to-find-cve-...
        
       | bryantwolf wrote:
       | All of this discourse seems very bizarre.
       | 
       | If smaller models can find these things, that doesn't mean mythos
       | is worse than we thought. It means all models are more capable.
       | 
       | Also if pointing models at files and giving them hints is all it
       | takes to make them find all kinds of stuff, well, we can also
       | spray and pray that pretty well with llms can't we.
       | 
       | It just points to us finding a lot more stuff with only a little
       | bit more sophistication.
       | 
       | Hopefully the growing pains are short and defense wins
        
         | davebren wrote:
         | > If smaller models can find these things, that doesn't mean
         | mythos is worse than we thought. It means all models are more
         | capable.
         | 
         | It means "it's so dangerous we can't release it" was a blatant
         | lie since anthropic would have already known this.
        
           | bryantwolf wrote:
           | Sure, I think it's reasonable to tell Anthropic the barn door
           | is already open.
           | 
           | Though, like, I guess I expect that when this comes out, all
           | the opus traffics will move over. It does appear to be much
           | more capable, just jury is out about how much more capable
        
           | pertymcpert wrote:
           | No one seems to have actually read the system card all the
           | way through.
           | 
           | The reason they didn't publish it was that it's orders of
           | magnitude more successful at _writing_ exploits vs Opus 4.6,
           | which only managed it something like 2% of the time.
        
       | abel_ wrote:
       | This misses the broader ongoing trend. For a few million dollars,
       | of course you can create a startup that builds tools it can use
       | to more efficiently find code vulnerabilities. And of course you
       | can do this with weaker models with scaffolds that incorporate
       | lots of human understanding. The difference now is that you don't
       | need an expensive team, nor a bunch of human heuristics, nor a
       | million dollars. The requisite cost and skill are falling
       | rapidly.
        
       | yalogin wrote:
       | Intuitively every existing model has already been trained on all
       | code, all vulnerabilities reported, all security papers. So they
       | all have the capability. Small models fall short because they may
       | not be able to find a vulnerability that spans across a large
       | function chain but for the most part they should suffice too.
       | 
       | Of course I say this without any knowledge of what mythos is
       | doing or how it's different. I am sure it's somehow different
        
         | nomel wrote:
         | Not intuitive at all. Not all models are equally capable, just
         | because they had the same training data. The model architecture
         | (as a whole) is very important. To reduce _capability_ , you
         | can reduce layers, tool use, thinking, quantize it, etc. This
         | is trivially proven by a cursory glance in the rough direction
         | of any set of benchmarks (or actual use).
         | 
         | Using small models as a classifier "there might be a
         | vulnerability here" is probably reasonable, if you have a model
         | capable of proving it. There are many companies attempting this
         | without the verification step, resulting in AI vulnerability
         | checker being banned left and right, from the nonsense noise.
        
       | omcnoe wrote:
       | The methodology here is completely wrong, outright dishonest.
       | 
       | Finding a needle in a haystack is easy if someone hands you the
       | small handful of hay containing the needle up front, and raises
       | their eyebrows at you saying "there might be a needle in this
       | clump of hay".
        
       | chopete3 wrote:
       | The impact of the Mythos announcement on the cybersecurity firms(
       | like Crowdstrike,ZScalar etc) is big enough(10-15% drop in stock
       | price) and this pushback is expected.
       | 
       | Companies like Aisle.com (the blog) and other VAPT companies
       | charge huge amounts to detect vulnerabilities.
       | 
       | If Cloud Mythos become a simple github hook their value will get
       | reduced.
       | 
       | That is a disruption.
        
         | zer00eyz wrote:
         | Crowdstrike, no pe because it just had its first profitable
         | quarter (38 million)
         | 
         | ZScalar No PE
         | 
         | Palo Alto Networks Inc (PANW) 86 PE
         | 
         | Fortinet : (FTNT) 31.63 PE
         | 
         | That last one, didn't get hit at all by the Mythos
         | announcement, because at some level it has at least some
         | grounding in fiscal reality.
        
         | throwa356262 wrote:
         | If anyone can get Crowdstrike to go bankrupt I will be rooting
         | for them.
         | 
         | Those guys are the reason our new work laptops run at 1/3 of
         | speed.
         | 
         | While back crowdstrike managed to simultaneously crash every
         | windows computer and bring every major company to a halt and
         | somehow are still around.
        
       | coppsilgold wrote:
       | LLMs are wordsmith oracles. A lot of effort went into trying to
       | coax interactive intelligence from them but the truth is that you
       | could have probably always harnessed the base models directly to
       | do very useful things. The instruct tuned models give your
       | harness even more degrees of freedom.
       | 
       | A while ago, the autoresearch[1] harness went viral, yet it's but
       | a highly simplified version of AlphaEvolve[2][3][4].
       | 
       | In the cybersecury context, you can envision a clever harness
       | that probes every function in a codebase for vulnerabilities,
       | then bubbles the candidates up to their callsites (and probes
       | whether the vulnerability can be triggered from there) and then
       | all the way to an interface (such as a syscall) where a potential
       | exploit can be manifested. And those would be the low hanging
       | fruit, other vulnerabilities may require the interplay of
       | multiple functions. Or race conditions.
       | 
       | [1] <https://github.com/karpathy/autoresearch>
       | 
       | [2] <https://deepmind.google/blog/alphaevolve-a-gemini-powered-
       | co...>
       | 
       | [3] <https://arxiv.org/abs/2506.13131>
       | 
       | [4] <https://github.com/algorithmicsuperintelligence/openevolve>
        
       | AlexandrB wrote:
       | The whole "this tool is too dangerous to be public" idea reeks of
       | marketing. Just like all the "AI is an existential threat" talk a
       | year ago. These companies are using ideas usually reserved for
       | something like nuclear weapons to make their products look more
       | impressive.
        
       | npilk wrote:
       | Wouldn't this mean we're even more cooked? I've seen this page
       | cited a few times as evidence that Mythos is no big deal, but if
       | true then the same big deal is already out there with other
       | models today.
        
         | davebren wrote:
         | As cooked as we were pre-LLMs knowing that security exploits
         | are relatively easy to learn about online and use, yet things
         | keep chugging along.
        
           | dominicq wrote:
           | This would just speed up the discovery -> patch cycle, at
           | least until such time that all the low hanging fruit
           | (=represented in training data) is patched.
           | 
           | Though another possibility would be that since LLMs generate
           | so much code, the LLM vulnerability discovery would just keep
           | chugging along and we'd simply settle for the same amount of
           | potential vulns, same relative vulnerability-exploit-patch
           | dynamics, though higher in absolute numbers.
        
       | slibhb wrote:
       | The best way to think of Anthropic's communication about Mythos
       | is as advertisement. It's basically "our model is too smart to
       | release" which suggests they're ahead of OpenAI (without proof)
        
         | pardon_me wrote:
         | The whole company is like that. If things were as amazing as
         | advertised, they wouldn't even need to advertise. Or to release
         | models to the public at all.
        
         | boelboel wrote:
         | Seen similar things with Openai and Palantir.
        
           | slibhb wrote:
           | Yes. OpenAI does the exact same thing.
        
       | charcircuit wrote:
       | The thesis that the system is more important than the model is
       | not bitter lesson pilled. I would not bet on this in the long
       | term. We will get to the point where you can just tell the model
       | to go find and classify the severity of all security problems
       | with a codebase.
        
       | midnitewarrior wrote:
       | At the center of every security situation is the question, "is
       | the effort worth the reward?"
       | 
       | We prepare security measures based on the perceived effort a bad
       | actor would need to defeat that method, along with considering
       | the harm of the measure being defeated. We don't build Fort Knox
       | for candy bars, it was built for gold bars.
       | 
       | These model advances change the equation. The effort and cost to
       | defeat a measure goes down by an order of magnitude or more.
       | 
       | Things nobody would have considered to reasonably attempt are
       | becoming possible. However. We have 2000-2020s security measures
       | in place that will not survive the AI models of 2026+. The
       | investment to resecure things will be massive, and won't come
       | soon enough.
        
       | _pdp_ wrote:
       | find ./ \( -name '*.c' -o -name '*.cpp' \) -exec agent.sh -p "can
       | you spot any vulnerabilities in {}" \;
        
       | abhinaystha wrote:
       | Tech companies are just hyping their model to that the bubble
       | wont burst so easily.
        
       | nfcampos wrote:
       | Anthropic marketing (and even supposedly technical write ups)
       | _sadly_ has become more hyperbole and less substance over time
       | imo. This technology is so impressive on its own, really feels
       | like shootings themselves in the foot in the long run, but what
       | do I know
       | 
       | Case in point here where they conveniently fail to report the
       | false positive rate, while also saying that if it wasn't for
       | Address Sanitizer discarding all the false positives this system
       | would have been next to useless
        
         | decidu0us9034 wrote:
         | Right now, we accept false positives as long as you can sort
         | them out. I think it's pretty typical that >99% of fuzzer runs
         | don't result in new coverage. Of course they're far from
         | useless without feedback but it's better to have it if you can.
         | I guess the question is does the llm approach have lower costs
         | for validation and triaging vs just fuzzing alone, unclear to
         | me. Anthropic would like people to believe automation is this
         | scary new unknown
        
       | palashdeb wrote:
       | Been tracking this since the blog post, quick a big deal they are
       | making it.
        
       | thywis wrote:
       | Sure, but it's more about whether the small model can find the
       | vulnerability that bigger model can.
        
       | mrinterweb wrote:
       | I feel like there have been enough hyperbolic claims by
       | Anthropic, that I'm starting to get some real Boy Who Cried Wolf
       | energy. I'm starting to tune out, and assume it is a marketing
       | ploy. Trust me, I'm an Antropic fan, and I pay my $200/month for
       | max, but the claims are wearing thin.
        
       | starboyy wrote:
       | Tagline is very funny
        
       | oliveiracwb wrote:
       | I trust miracle models about as much as I trust my uncle's memes
       | or three-day prosperity courses.
        
       | etothet wrote:
       | My big question around the Mythos FUD, is this: if we take for
       | fact the Mythos is as powerful and dangerous as we're being told
       | (and I realize this is part marketing), and because of that
       | Anthropic isn't going to release it...how long can that last?
       | Isn't it reasonable that OpenAI or xAI or some other company - or
       | foreign government - will come up with a similarly dangerous
       | model fairly soon?
       | 
       | So what's Anthropic's plan here? How long can they withhold
       | releasing Mythos or something Mythos-like? Is it reasonable to
       | think they - or another AI provider - are going to dumb down
       | future models so they're less dangerous? I personally don't think
       | that's the case.
       | 
       | I'm not saying Anthropic should or shouldn't release Mythos, but
       | it leaves me wonderingwhat's going to be different in, say, 6
       | months or even a year when they or another provider releases a
       | model as dangerous as we're being told Mythos is?
        
       | dev1ycan wrote:
       | It was obvious since the start that 1)it's probably all
       | javascript based or android websites/programs that contain a ton
       | of "vulnerable" libraries (or really old closed sourced c++
       | code).
       | 
       | Also you're not helping your case as a software company if you
       | feed your code to an LLM, great job making it all public, because
       | it will most likely be used as training data like it or not.
        
       | Animats wrote:
       | What are they finding? Buffer overflows? Something else?
       | 
       | Also, if someone has the time and tokens, would they please run
       | the OpenJPEG 2000 decoder through this tester? It's known to be
       | brittle. The data format has lots of offsets, and it's permitted
       | to truncate the file to get a lower-rez version. That combo leads
       | to trouble.
        
       | ares623 wrote:
       | Once again, it would've been so easy and simple to remove all
       | doubt from their claims: release all the tools and harnesses they
       | used to do it and allow 3rd parties to try and replicate their
       | results using different models. If Mythos itself is as big a moat
       | as they claim it is, then there shouldn't be any problem here.
       | 
       | They did the same stunt with the C compiler. They could've
       | released a tool to let others replicate it, but they didn't.
        
       | StrauXX wrote:
       | A lot of comments here are dismissing this post because the
       | relevant code was isolated. But thats the exact same thing
       | Anthropic did with Mythos! They describe their (very lean)
       | harness in the Anthropic Red Mythos blog post. The harness first
       | assigns each file in the given codebase an importance value. Then
       | points claude code at the cpdebase with a prompt stating that it
       | should focus on that file. It spawns a claude code instances for
       | each file in the codebase.
       | 
       | So no, the fact that the posters isolated the relevant code does
       | not invalidate their findings.
       | 
       | [1] https://red.anthropic.com/2026/mythos-preview/
        
         | make_it_sure wrote:
         | check other comments, they didn't
        
         | felipeerias wrote:
         | From the article:
         | 
         | > Our tests gave models the vulnerable function directly, often
         | with contextual hints (e.g., "consider wraparound behavior").
        
           | grandinquistor wrote:
           | I mean you can still scale that? Ask a lighter model to go
           | through every function to find vulnerabilities, take output
           | to bigger model like Opus and classify the critical ones.
        
       | jeffrwells wrote:
       | Anthropic has become a PR vaporware company
        
       | pugazh35 wrote:
       | Maybe P vs NP, plays a silent role in it
        
       | tonymet wrote:
       | My router had a broken IPv6 firewall and lacked root access. I
       | needed a root shell to run ip6tables. I exfil'd the code and ran
       | Gemini to discover shell injection vulnerabilities. I was able to
       | get root shell to run ip6tables and add the firewall. I had
       | notified the vendor for a couple years that the firewall was
       | broken and showed them the issue but it hadn't been fixed.
        
       | make_it_sure wrote:
       | The only reason that's on top of HN is that people really want
       | Mythos to be bad. This "study" is a cheap gimmick, they pointed
       | to the actual location with the vulnerability and said "something
       | is bad here, find it".
       | 
       | The hardest part is locating the issue, if you point directly to
       | it, you're not comparing the same thing by far, and they know it.
       | This was just a stunt by them to get publicity, they knew what
       | they were doing and many fell for it, including here.
        
         | stringfood wrote:
         | Case in point: I found the same OpenBSD bug once I knew where
         | it was and I am highly uneducated
        
       | onesociety2022 wrote:
       | This article is written by a company building an AI cybersecurity
       | solution. Not sure how much you can trust them on this topic -
       | their business will get destroyed if Mythos is actually so
       | superior to existing models that it doesn't require a big
       | investment into the scaffold/harness to find security
       | vulnerabilities. If the model is too good, then what's the value
       | of their solution?
        
       | muyuu wrote:
       | I think the "Mythos" name is genius. The people at Anthropic make
       | a bunch of claims and the public is expected to just believe them
       | without any possibility of testing those claims or reproducing
       | those results, and since so many people are invested in this
       | saviour for the Global economy, or in the industry in general, or
       | in hype to feed their engagement-based income sources, then there
       | is faith to spare.
       | 
       | Meanwhile this mythical beast wasn't able to prevent the Bun
       | vulnerability that exposed their code, let alone precluding the
       | need to acquire that IP in the first place for presumably
       | hundreds of millions of $$$, instead of coding a better
       | replacement or a solution of its own.
       | 
       | What is real and measurable is that subscription plan users are
       | getting a much degraded service for the same money through both
       | open and hidden policies, while Anthropic moves compute to serve
       | off-the-counter customers. The same people who come with the most
       | obvious and brazen lies to dismiss the clear degradation of their
       | service also come with this "security" justification for a move
       | that looks just like good old market segmentation which would
       | perfectly fit the strong symptoms that they cannot afford to
       | offer tokens at a competitive price in this market.
        
         | tokioyoyo wrote:
         | There are two possibilities:
         | 
         | a) Anthropic is lying, and every company that is collaborating
         | on vulnerability squishing project is an accomplice in this big
         | lie b) Anthropic has then goldest gold of the shovels to sell
         | to people, which is actually useful for enterprises
         | 
         | Everyone, including Ant, understands that other companies will
         | catch up in terms of model strength. So it's a damned if you
         | do, damned if you don't position wrt releasing it to the
         | public.
        
           | phire wrote:
           | The model is probably legitimately better. But it might not
           | be enough better to justify the extra cost of inference.
           | 
           | They know if they released it publicly, people will be able
           | to see exactly how smart it is, and adjust their demand
           | correspondingly. Anthropic will either need to price it high
           | enough that nobody uses it (and the hardware is sitting
           | mostly idle to servicing a few customers), or lower their
           | profit margins (potentially below cost) to price it fairly.
           | 
           | So instead, they bundle it with this fancy new exploit
           | finding scaffold, and sell the combined it to enterprise
           | customers. I bet the scaffold works fine with smaller models,
           | but gets notably improved results with Mythos.
           | 
           | The two products support each-other, and with the exclusive
           | bundle Anthropic can get more profit selling both together
           | than they would get selling them individually.
           | 
           | And as an added bonus, people over estimate the capability of
           | this unreleased model, providing hype for Anthropic.
        
         | JSR_FDED wrote:
         | One very clever consequence of Anthropic's guarded release of
         | the Mythos model is that they've kind of claimed the position
         | of best in class here, and also positioned themselves as the
         | responsible vendor in this space in one fell swoop.
        
           | muyuu wrote:
           | OpenAI pulled the same trick with GPT3. It's amazing how well
           | it's working judging by the comments I'm hearing from people
           | I know exist. Because out there on social media, who knows.
        
         | kilroy123 wrote:
         | Well said. I really hope the Chinese models keep getting
         | better. Competition is good.
        
       | nickpsecurity wrote:
       | We've always had good tools for program analysis and testing.
       | They're usually exhorbitantly expensive.
       | 
       | I'm hoping the good results with AI models drive down the prices
       | of traditional tools. Then, we can train open models to integrate
       | with them.
        
       | morpheuskafka wrote:
       | Everyone is commenting that this doesn't count because they
       | pointed it at the specific files that Mythos already found
       | vulnerable.
       | 
       | But sometimes you do know where vulnerabilities are and still
       | don't know what they are. For example, an update may be released
       | in beta changing the part of the Mac or Windows kernel or some
       | app, but they haven't published the CVE yet. If locally runnable
       | (even with significant compute costs) LLMs can find and exploit
       | it based on either the location of the changed file or the actual
       | diff of the compiled output, we could see exploits before the
       | update ever went to production?
        
       | jurschreuder wrote:
       | All these models will completely mess up your code if you let
       | them.
       | 
       | And if they constantly scan your code with various settings and
       | updates you will spend hours a day reading, trying to understand
       | locally coherent but structurally incoherent vibes trying to
       | pinpoint the exact reasoning flaw. Exhausting.
        
         | Loeffelmann wrote:
         | > locally coherent but structurally incoherent
         | 
         | Perfectly summarizes what I hate about AI code. The diff looks
         | fine but if you take a step back its an absolute mess. I mean
         | have you looked at the Claude Code or Openclaw codebases? that
         | is the result of full on vibecoded. A bloated unattainable mess
         | that no one understands.
        
       | rurban wrote:
       | If they would have watched Carlini's "unblocked" talk on youtube,
       | which is much more detailed than the blog post, they would not
       | need this writeup. He was worried about the reproducers of the
       | zero-day's. Not the actual zero-days that much.
        
       | solatic wrote:
       | Most commenters here: "Mythos is powerful because you can point
       | it at a whole codebase, if you point the smaller models at a
       | whole codebase and iterate through small sections of code, you'll
       | get too many false-positives to handle."
       | 
       | This misses the point entirely. You pay $20k as a one-time fee to
       | establish a baseline. Your codebase develops one PR at a time,
       | which... updates isolated sections of code. Which means you don't
       | need Mythos for a PR, just small, open-weight models. _Maybe_ you
       | run Mythos once a year to ensure that you keep your baseline
       | updated and reduce the risk that the open-weights models missed
       | anything.
       | 
       | Seeing this as anything but a huge win for open-weights models
       | and a huge loss for Anthropic misses the point entirely. Mythos
       | isn't something you can persuade Fortune 500 companies to spend
       | $20k/day or even $20k/week to spend on, like they were hoping
       | for. $20k/year is a lot less valuable, and it won't justify
       | development costs or Anthropic's growth multiple.
        
       | bottlepalm wrote:
       | None of these comments will age well. I don't know if it is
       | denial, or cope, or being threatened by AI or what, but no one is
       | taking AI serious enough. Simply take what is being presented at
       | face value, stop thinking everything is a conspiracy and realize
       | the implications. Zero days in software are one thing, it's a hop
       | skip and jump from there to zero days in biology - and no one
       | will be laughing about that.
        
       | latentframe wrote:
       | Good writeup seems like it's not really the big model against the
       | small one anymore and if smaller models can do most of the job
       | once the context is smaller then it's more about the system
       | around them and the expertise ...
        
       | brador wrote:
       | I want that Doom thing but finding vulnerabilities using AI
       | models.
       | 
       | Like I discovered a JavaScript vulnerability using a fridge.
        
       | high_byte wrote:
       | "The correct answer: not currently vulnerable, but the code is
       | fragile and one refactor away from being exploitable."
       | 
       | absolutely. I see this pattern all the time when doing security
       | audits - code that is nearly-vulnerable. I would mark these
       | things as informational and recommend to harden them anyway, and
       | any model would do a good job to do the same.
        
       | JoshTko wrote:
       | I bet Anthropic just had marketing strategy discussions with
       | Mythos to get the "breakthrough hacking tool!" framing.
        
       | ptrwis wrote:
       | When you pair-programming with AI, even Haiku is very good. Just
       | treat is as you assistant.
        
       | tom-blk wrote:
       | Interesting comparison, cool article!
        
       | HarHarVeryFunny wrote:
       | Most of the comments here seems to be responding to the issue of
       | finding vulnerabilities, rather than exploiting them, but the
       | Anthropic claim is that the Mythos advance is being able to
       | actually develop exploits whereas Opus 4.6 had been able to find
       | vulnerabilities, but was poor at being able to develop exploits
       | for them.
       | 
       | It's also noteworthy that Anthropic attributes Mythos'
       | improvement to advances in "coding, reasoning and autonomy", and
       | that the autonomy part seems especially important since they go
       | on to say that trying to develop exploits included adding debug
       | code to projects, running them under a debugger, etc.
       | 
       | When comparing the capabilities of Mythos to previous generation
       | and/or smaller models, it seems it would therefore be useful to
       | distinguish between identifying potential vulnerabilities and
       | actually trying to build exploits for them in agentic fashion.
       | Finding the "needle in a haystack" (potential vulnerability) is
       | one aspect, but the other part is an agentic exploit-writing
       | harness being handed the needle and asked to try to exploit it.
       | 
       | I wonder how much effort Anthropic put into building the
       | harnesses and environments for Mythos to run, modify and debug
       | code? For example, was Mythos set up to be able to build and run
       | a modified BSD in some virtual environment, or did it just take
       | suspect functions and test those in isolation?
       | 
       | It'd be interesting to put the capabilities of Opus 4.6, Mythos,
       | and other models into perspective by comparing them to
       | traditional non-AI static analysis security scanning tools.
       | Anthropic mention that the open source projects they scanned came
       | from the OSS-Fuzz corpus, but as far as I can see they don't say
       | what other tools have, or have not, been used to scan these
       | projects.
       | 
       | It'd also be interesting to know to what extent Mythos was
       | explicitly RL trained to develop exploits (especially since it
       | sounds as if Anthropic have the dataset and environment needed to
       | do this) as opposed to this just being a natural consequence of
       | the model being better. If this was the case then it might be a
       | large part of why they are not releasing it - can't really
       | position yourself as strong on security if you deliberately
       | develop and release a hacking tool!
        
       ___________________________________________________________________
       (page generated 2026-04-12 23:01 UTC)