[HN Gopher] Vulnerability research is cooked
       ___________________________________________________________________
        
       Vulnerability research is cooked
        
       Author : pedro84
       Score  : 101 points
       Date   : 2026-03-30 18:43 UTC (4 hours ago)
        
 (HTM) web link (sockpuppet.org)
 (TXT) w3m dump (sockpuppet.org)
        
       | nitros wrote:
       | I'm suspicious of this prediction given the curl project's
       | experiences...
        
         | tptacek wrote:
         | Everybody agrees that idiots were spamming curl with random
         | just-plausible-enough-seeming output from old models.
        
           | tomjakubowski wrote:
           | It sounds like what makes the pipeline in the article
           | effective is the second stage, which takes in the
           | vulnerability reports produced by the first level and
           | confirms or rejects them. The article doesn't say what the
           | rejection rate is there.
           | 
           | I don't think the spammers would think to write the second
           | layer, they would most likely pipe the first layer (a more
           | naive version of it too, probably) directly to the issue
           | feed.
        
             | tptacek wrote:
             | There are at least three differences:
             | 
             | * Carlini's team used new frontier models that have gotten
             | materially better at finding vulnerabilities (talk to
             | vulnerability researchers outside the frontier labs,
             | they'll echo that). Stenberg was getting random slop from
             | people using random models.
             | 
             | * Carlini's process is iterated exhaustively over the whole
             | codebase; he's not starting with a repo and just saying
             | "find me an awesome bug" and taking that and only that
             | forward in the process.
             | 
             | * And then yes, Carlini is qualifying the first-pass
             | findings with a second pass.
        
         | wslh wrote:
         | The problem is that you have all kind of "security spam" in the
         | same way that social media is flooded by automatic, but on-
         | topic, content. This doesn't mean that some very few reports
         | are not correct.
         | 
         | One way to filter that out could be to receive the PoC of the
         | exploit, and test it in some sandbox. I think what XBOW and
         | others are doing is real.
        
         | jerf wrote:
         | The people spamming curl did step one, "write me a
         | vulnerability report on X" but skipped step two, "verify for me
         | that it's actually exploitable". Tack on a step three where a
         | reasonably educated user in the field of security research does
         | a sanity check on the vulnerability implementation as well and
         | you'll have a pipeline that doesn't generate a ton of false
         | positives. The question then will rather be how cost-effective
         | it is for the tokens and the still-non-zero human time
         | involved.
        
         | MajesticHobo2 wrote:
         | That was then, this is now. The new models are scarily good. If
         | you're skeptical, just take an hour to replicate the strategy
         | the article references. Point Claude at any open-source
         | codebase you find interesting and instruct it to find
         | exploitable vulnerabilities. Give it a well-defined endpoint if
         | you want (e.g., "You must develop a Python script that triggers
         | memory corruption via a crafted request") and see how well it
         | does.
        
           | phyzome wrote:
           | > That was then, this is now.
           | 
           | No, what we were seeing with curl was script kiddies. It
           | wasn't about the quality of the models at all. They were not
           | filtering their results for validity.
        
             | MajesticHobo2 wrote:
             | It was definitely partially about model quality. The
             | frontier models are capable of producing valid findings
             | with (reasonably) complex exploit chains on the first pass
             | (or with limited nudging) and are much less prone to making
             | up the kinds of nonsensical reports that were submitted to
             | curl. Compared to now, the old models essentially didn't
             | work for security.
             | 
             | If those script kiddies had been using today's models
             | instead and _still_ didn't do any filtering, a lot more of
             | those bugs would have been true positives.
        
       | tomjakubowski wrote:
       | > Now consider the poor open source developers who, for the last
       | 18 months, have complained about a torrent of slop vulnerability
       | reports. I'd had mixed sympathies, but the complaints were at
       | least empirically correct. That could change real fast. The new
       | models find real stuff.
       | 
       | The slop reports won't stop just because real ones are coming in.
       | If the author's right, open source maintainers will still will
       | have to deal with the torrent of slop: _on top of_ triaging and
       | identifying the legit vulnerabilities. Obviously, this is just
       | another role for AI models to fill.
        
       | stavros wrote:
       | I don't understand why the takeaway here is (unless I'm missing
       | something), more or less "everything is going to get exploited
       | all the time". If LLMs can really find a ton of vulnerabilities
       | in my software, why would I not run them and just patch all the
       | vulnerabilities, leading to perfectly secure software (or, at the
       | very least, software for which LLMs can no longer find any new
       | vulnerabilities)?
        
         | tptacek wrote:
         | That might be one outcome, especially for large, expertly-
         | staffed vendors who are already on top of this stuff. My real
         | interest in what happens to the field for vulnerability
         | researchers.
        
           | lifty wrote:
           | Perhaps a meta evolution, they become experts at writing
           | harnesses and prompts for discovering and patching
           | vulnerabilities in existing code and software. My main
           | interest is, now that we have LLMs, will the software
           | industry move to adopting techniques like formal verification
           | and other perhaps more lax approaches that massively increase
           | the quality of software.
        
           | stavros wrote:
           | True, but I already am curious to see what happens in a
           | multitude of fields, so this is just one more entry in that
           | list.
        
           | underdeserver wrote:
           | Just wanted to point out that tptacek is the blog post's
           | author (and a veteran security researcher).
        
         | layer8 wrote:
         | The pressure to do so will only happen as a consequence of the
         | predicted vulnerability explosion, and not before it. And it
         | will have some cost, as you need dedicated and motivated people
         | to conduct the vulnerability search, applying the fixes, and
         | re-checking until it comes up empty, before each new
         | deployment.
         | 
         | The prediction is: _Within the next few months, coding agents
         | will drastically alter both the practice and the economics of
         | exploit development. Frontier model improvement won't be a slow
         | burn, but rather a step function. Substantial amounts of high-
         | impact vulnerability research (maybe even most of it) will
         | happen simply by pointing an agent at a source tree and typing
         | "find me zero days"._
        
           | cartoonworld wrote:
           | I feel like the dream of static analysis was always a pipe.
           | 
           | When the payment for vulns drops i'm wondering where the
           | value is for hackers to run these tools anymore? The LLMs
           | don't do the job for you, testing is still a LOT OF WORK.
        
         | zar1048576 wrote:
         | My sense is that the asymmetry is non-trivial issue here. In
         | particular, a threat actor needs one working path, defenders
         | need to close all of them. In practice, patching velocity is
         | bounded by release cycles, QA issues / regression risk, and a
         | potentially large number of codebases that need to be looked
         | at.
        
         | Veserv wrote:
         | When did we enter the twilight zone where bug trackers are
         | consistently empty? The limiting factor of bug reduction is
         | remediation, not discovery. Even developer smoke testing
         | usually surfaces bugs at a rate far faster than they can be
         | fixed let alone actual QA.
         | 
         | To be fair, the limiting factor in remediation is usually
         | finding a reproducible test case which a vulnerability is by
         | necessity. But, I would still bet most systems have plenty of
         | bugs in their bug trackers which are accompanied by a
         | reproducible test case which are still bottlenecked on
         | remediation resources.
         | 
         | This is of course orthogonal to the fact that patching systems
         | that are insecure by design into security has so far been a
         | colossal failure.
        
           | reactordev wrote:
           | That might have been true pre LLMs but you can literally
           | point an agent at the queue until it's empty now.
        
             | batshit_beaver wrote:
             | You literally cannot, since ANY changes to code tend to
             | introduce unintended (or at least not explicitly requested)
             | new behaviors.
        
               | reactordev wrote:
               | I've had mine on a Ralph loop no problem. Just review the
               | PR..
        
               | k_roy wrote:
               | Which still means a single person with Claude can clear a
               | queue in a day versus a month with a traditional team.
        
               | lll-o-lll wrote:
               | Eventual convergence? Assuming each defect fix has a 30%
               | chance of introducing a new defect, we keep cycling until
               | done?
        
               | Kinrany wrote:
               | Why would it converge?
        
               | saintfire wrote:
               | Assuming you can catch every new bug it introduces.
               | 
               | Both assumptions being unlikely.
               | 
               | You also end up with a code base you let an AI agent
               | trample until it is satisfied; ballooned in complexity
               | and redudant brittle code.
        
               | charcircuit wrote:
               | You can have an AI agent refactor and improve code
               | quality.
        
             | bsder wrote:
             | The fact that KiCad still has a ton of highly upvoted
             | missing features and the fact that FreeCAD still hasn't
             | solved the topological renumbering problem are existence
             | proofs to the contrary.
        
         | Buttons840 wrote:
         | > If LLMs can really find a ton of vulnerabilities in my
         | software, why would I not run them and just patch all the
         | vulnerabilities, leading to perfectly secure software?
         | 
         | Probably because it will be a felony to do so. Or, the threat
         | of a felony at least.
         | 
         | And this is because it is very embarrassing for companies to
         | have society openly discussing how bad their software security
         | is.
         | 
         | We sacrifice national security for the convenience of
         | companies.
         | 
         | We are not allowed to test the security of systems, because
         | that is the responsibility of companies, since they own the
         | system. Also, companies who own the system and are responsible
         | for its security are not liable when it is found to be insecure
         | and they leak half the nations personal data, again.
         | 
         | Are you seeing how this works yet? Let's not have anything like
         | verifiable and testable security interrupt the gravy train to
         | the top. Nor can we expect systems to be secure all the time,
         | be reasonable.
         | 
         | One might think that since we're all in this together and all
         | our data is getting leaked twice a month, we could work
         | together and all be on the lookout for security vulnerabilities
         | and report them responsibly.
         | 
         | But no, the systems belong to companies, and they are solely
         | responsible. But also (and very importantly) they are not
         | responsible and especially they are not financially liable.
        
           | gruez wrote:
           | >> If LLMs can really find a ton of vulnerabilities in my
           | software, why would I not run them and just patch all the
           | vulnerabilities, leading to perfectly secure software?
           | 
           | >Probably because it will be a felony to do so. Or, the
           | threat of a felony at least.
           | 
           | "my software" implies you own it (ie. your SaaS), so CFAA
           | isn't an issue. I don't think he's implying that vigilante
           | hackers should be hacking gmail just because they have a
           | gmail account.
        
         | htrp wrote:
         | Attackers only have to be successful once while defenders have
         | to be successful all the time?
        
         | joatmon-snoo wrote:
         | Breaking something is easier than fixing it.
        
           | tptacek wrote:
           | People have said that for decades and it wasn't true until
           | recently.
        
             | underdeserver wrote:
             | Specifically in software vulnerability research, you mean.
             | 
             | Fixing vulnerable code is usually trivial.
             | 
             | In the physical world breaking things is usually easier.
        
           | charcircuit wrote:
           | A proper fix maybe. But LLMs can easily make it no longer
           | exploitable in most cases.
        
       | spr-alex wrote:
       | I interned for the author at 18. I assumed security testing
       | worked like this:
       | 
       | 1. Static analysis catches nearly all bugs with near-total code
       | coverage
       | 
       | 2. Private tooling extends that coverage further with better
       | static analysis and dynamic analysis, and that edge is what makes
       | contractors valuable
       | 
       | 3. Humans focus on design flaws and weird hardware bugs like
       | cryptographic side-channels from electromagnetic emanations
       | 
       | Turns out finding all the bugs is really hard. Codebases and
       | compiler output have exploded in complexity over 20 years which
       | has not helped the static analysis vision. Todays mitigations are
       | fantastic compared to then, but just this month a second 0day
       | chain got patched on one of the best platforms for hardware
       | mitigations.
       | 
       | I think LLMs get us meaningfully closer to what I thought this
       | work already was when I was 18 and didn't know anything.
        
         | cartoonworld wrote:
         | lots of security issues form at the boundaries between
         | packages, zones, services, sessions, etc. Static analysis could
         | but doesn't seem to catch this stuff from my perspective. Bugs
         | are often chains and that requires a lot of creativity,
         | planning etc
         | 
         | consider logic errors and race conditions. Its surely not
         | impossible for llm to find these, but it seems likely that
         | you'll need to step throught the program control flow in order
         | to reveal a lot of these interactions.
         | 
         | I feel like people consider LLM as free since there isn't as
         | much hand-on-keyboard. I kinda disgree, and when the cost of
         | paying out these vulns falls, I feel like nobody is gonna wanna
         | eat the token spend. Plenty of hackers already use ai in their
         | workflows, even then it is a LOT OF WORK.
        
         | Legend2440 wrote:
         | Catching all bugs with static analysis would involve solving
         | the halting problem, so it's never going to happen.
        
           | IsTom wrote:
           | A lot of software doing useful work halts pretty trivialy,
           | consuming inputs and doing bounded computation on each of
           | them. You're not going to recurse much in click handlers or
           | keep making larger requests to handle the current one.
        
       | badgersnake wrote:
       | Another boring AI hype article.
       | 
       | "The next model will be the one. Trust me. Just one more
       | iteration."
        
       | streetfighter64 wrote:
       | > Is the Linux KVM hypervisor connected to the hrtimer subsystem,
       | workqueue, or perf_event? The model knows.
       | 
       | I asked ChatGPT and it claimed "all three". Any linux wizards who
       | can confirm or deny?
       | 
       | Anyway, in my experience using mainly the Claude chat to do some
       | basic (not security) bug hunting, it usually fixates on one
       | specific hypothesis, and it takes some effort to get it off that
       | wrong track, even when I already know it's barking up the wrong
       | tree.
        
         | tptacek wrote:
         | It's all three, I just had it on the brain when I was writing
         | this.
        
           | streetfighter64 wrote:
           | Hm, kind of a strange question then, no? Is a car's engine
           | connected to the fuel tank, the wheels or the accelerator
           | pedal?
        
             | tptacek wrote:
             | I don't know, maybe it is? My point is just that frontier
             | models start off with latent models of all the
             | interconnectivity in all the important open-source
             | codebases, to a degree that would be infeasible for the
             | people who learned how all the CSS object lifecycles and
             | image rendering and unicode shaping stuff worked well
             | enough to use them in exploits.
        
         | jgeralnik wrote:
         | The wonderful thing though is that you can just run the model
         | multiple times (even in parallel). Some instances might get
         | stuck but as long as some find the bug and you have a good way
         | to filter outputs (e.g. with another llm that tries to create
         | concrete exploits) even a very small success rate on stage 1
         | can lead to reliable exploits
        
       | staticassertion wrote:
       | > Everything is up in the air. The industry is sold on memory-
       | safe software, but the shift is slow going. We've bought time
       | with sandboxing and attack surface restriction. How well will
       | these countermeasures hold up? A 4 layer system of sandboxes,
       | kernels, hypervisors, and IPC schemes are, to an agent, an
       | iterated version of the same problem. Agents will generate full-
       | chain exploits, and they will do so soon.
       | 
       | I think this is the interesting bit. We have some insanely
       | powerful isolation technology and mitigations. I can put a
       | webassembly program into a seccomp'd wrapper in an unprivileged
       | user into a stripped down Linux environment inside of
       | Firecracker. An attacker breaking out of that feels like science
       | fiction to me. An LLM could do it but I think "one shots" for
       | this sort of attack are extremely unlikely today. The LLM will
       | need to find a wasm escape, then a Linux LPE that's reachable
       | from an unprivileged user with a seccomp filter, then once they
       | have kernel control they'll need to manipulate the VM state or
       | attack KVM directly.
       | 
       | A human being doing those things is hard to imagine. Exploitation
       | of Firecracker is, from my view, extremely difficult. The bug
       | density is very low - code quality is high and mitigation
       | adoption is a serious hurdle.
       | 
       | Obviously people aren't just going to deploy software the way I'm
       | suggesting, but even just "I use AWS Fargate" is a crazy barrier
       | that I'm skeptical an LLM will cross.
       | 
       | > Meanwhile, no defense looks flimsier now than closed source
       | code.
       | 
       | Interesting, I've had sort of the opposite view. Giving an LLM
       | direct access to the semantic information of your program, the
       | comments, etc, feels like it's just handing massive amounts of
       | context over. With decompilation I think there's a higher risk of
       | it missing the intention of the code.
       | 
       | edit: I want to also note that with LLMs I have been able to do
       | sort of insane things. A little side project I have uses iframe
       | sandboxing _insanely_ aggressively. Most of my 3rd party
       | dependencies are injected into an iframe, and the content is
       | rendered in that iframe. It can communicate to the parent over a
       | restricted MessageChannel. For cases like  "render markdown" I
       | can even leverage a total-blocking CSP within the sandbox.
       | Writing this by hand would be silly, I can't do it - it's like
       | building an RPC for every library I use. "Resize the window" or
       | "User clicked this link" etc all have to be written individually.
       | But with an LLM I'm getting sort of silly levels of safety here -
       | Chrome is free to move each iframe into its own process, I get
       | isolated origins, I'm immune from supply chain vulnerabilities,
       | I'm immune to _mostly_ immune to XSS (within the frame, where
       | most of the opportunity is) and CSRF is radically harder, etc.
       | LLMs have made adoption of Trusted Types and other mitigations
       | insanely easy for me and, IMO, these sorts of mitigations are
       | more effective at preventing attacks than LLMs will be at finding
       | bypasses (contentious and platform dependent though!). I suppose
       | this doesn 't have any bearing on the direct position of the blog
       | post, which is scoped to the new role for vulnerability research,
       | but I guess my interest is obviously going to be more defense
       | oriented as that's where I live :)
        
         | MajesticHobo2 wrote:
         | > With decompilation I think there's a higher risk of it
         | missing the intention of the code.
         | 
         | I'm not sure but suspect the lack of comments and documentation
         | might be an advantage to LLMs for this use case. For
         | security/reverse engineering work, the code's actual behavior
         | matters a lot more than the developer's intention.
        
           | staticassertion wrote:
           | I think the other side of that is that mismatches between
           | intention and implementation are exactly where you're going
           | to find vulnerabilities. The LLM that looks at closed source
           | code has to guess the intention to a greater degree.
        
             | moyix wrote:
             | This is true for a lot of things but for low-level code you
             | can always fall back to "the intention is to not violate
             | memory safety".
        
               | staticassertion wrote:
               | That's true, but certainly that's limiting. Still, even
               | then, `# SAFETY:` comments seem extremely helpful. "For
               | every `unsafe`, determine its implied or stated safety
               | contract, then build a suite of adversarial tests to
               | verify or break those contracts" feels like a great way
               | to get going.
        
               | moyix wrote:
               | It's limiting from the PoV of a developer who wants to
               | ensure that their own code is free of all security
               | issues. It is not limiting from the point of view of an
               | attacker who just needs one good memory safety vuln to
               | win.
        
       | rubiquity wrote:
       | I was distracted by the picture of the ingredients to a Final
       | Ward being at the top of the page.
        
       | narginal wrote:
       | Just like how fuzzers will find all the bugs, right? Right??
       | There's definitely infrastructure at these big companies that
       | isn't sitting in a while loop 'fuzzing' right? Why is it news
       | that vulnerability research will continue to get harder, exactly?
       | It has always been this way, exploits will get more expensive,
       | and the best researchers will continue with whatever tools they
       | find useful.
        
         | tptacek wrote:
         | It's a good question. Fuzzers generated a surge of new
         | vulnerabilities, especially after institutional fuzzing
         | clusters got stood up, and after we converged on coverage-
         | guided fuzzers like AFL. We then got to a stable equilibrium, a
         | new floor, such that vulnerability research & discovery doesn't
         | look that drastically different after fuzzing as before.
         | 
         | Two things to notice:
         | 
         | * First, fuzzers also generated and continue to generate large
         | stacks of unverified crashers, such that you can go to archives
         | of syzkaller crashes and find crashers that actually work. My
         | contention is that models are not just going to produce
         | hypothetical vulnerabilities, but also working exploits.
         | 
         | * Second, the mechanism 4.6 and Codex are using to find these
         | vulnerabilities is nothing like that of a fuzzer. A fuzzer
         | doesn't "know" it's found a vulnerability; it's a simple
         | stimulus/response test (sequence goes in, crash does/doesn't
         | come out). Most crashers aren't exploitable.
         | 
         | Models can use fuzzers to find stuff, and I'm surprised that
         | (at least for Anthropic's Red Team) that's not how they're
         | doing it yet. But at least as I understand it, that's generally
         | _not_ what they 're doing. It something much closer to static
         | analysis.
        
           | staticassertion wrote:
           | I suspect we'll see combinations of symbolic execution +
           | fuzzing as contextual inputs to LLMs, with LLMs delegating
           | highly directed tasks to these external tools that are
           | radically faster at exploring a space with the LLM guiding
           | based on its own semantic understanding of the code.
           | 
           | I'm with you, I expected this to be happening already. Funny
           | enough, I guess even a hardened codebase isn't at that level
           | of "we need to optimize this" currently so you can just throw
           | tokens at the problem.
        
             | tptacek wrote:
             | Right, so that's exactly how I was thinking about it
             | _before_ I talked to Carlini. Then I talked to Carlini for
             | the SCW podcast. Then I wrote this piece.
             | 
             | I don't know that I'm ready to say that the frontier of
             | vulnerability research with agents is modeling, fuzzing,
             | and analysis (orchestrated by an agent). It may very well
             | be that the models themselves stay ahead of this for quite
             | some time.
             | 
             | That would be a super interesting result, and it's the
             | result I'm writing about here.
        
           | narginal wrote:
           | I have just seen too much infrastructure set up to 'find
           | bugs,' effectively sitting and doing nothing- either the
           | wrong thing gets audited, or tons of compute gets thrown at a
           | code base and nobody ever checks in on or verifies.
           | 
           | This seems like a human/structural issue that an AI won't
           | actually fix - attackers/defenders alike will gain access to
           | the same models, feels a little bit like we are back to
           | square one
        
             | tptacek wrote:
             | If that's true, and if patches can effectively be pushed
             | out quickly, then the results of this will be felt mostly
             | by vulnerability researchers, which is the subject of the
             | piece. But those are big "ifs".
        
       | stackghost wrote:
       | I was doing TryHackMe's "advent of cyber" sidequest last
       | christmas and used a process very much like Carlini's that is
       | outlined in TFA.
       | 
       | >I'm doing a CTF. I popped a shell on this box and found this
       | binary. Here is a ghidra decompilation. Is there anything
       | exploitable in $function?
       | 
       | You can't just ask Claude or ChatGPT to do the binex for you, but
       | even last year's models were really good at finding heap or stack
       | vulns this way.
        
       | thadt wrote:
       | So the intersting question: are we long term safer with "simpler"
       | closer to hardware memory unsafe(ish) environments like Zig, or
       | is the memory safe but more abstract feature set of languages
       | like Rust still the winning direction?
       | 
       | If a hypothetical build step is "look over this program and
       | carfully examine the bounds of safety using your deep knowledge
       | of the OS, hardware, language and all the tools that come along
       | with it", then a less abstract environment might be at an overall
       | advantage. In a moment, I'll close this comment and go back to
       | writing Rust. But if I had the time (or tooling) to build
       | something in C and test it as thoroughly as say, SQLite [1], then
       | I might think harder about the tradeoffs.
       | 
       | [1] https://sqlite.org/whyc.html
        
         | love2read wrote:
         | What about this article raises this question? If anything, this
         | article makes it pretty clear that memory safe languages are a
         | win. It seems like a serious disadvantage to require a
         | nondeterministic program to evaluate your code's safety.
        
       | tonymet wrote:
       | I agree AI makes exploits more accessible, it also makes pen-
       | testing and finding vulns more accessible, in both early and late
       | stages of product development.
       | 
       | AI has saved me a ton of money and time auditing. Mostly because
       | I'm tired / lazy.
       | 
       | It's both a black pill & white pill, and if we have the right
       | discipline, a tremendous white pill. Engineers can no longer
       | claim to be "cost effective" by ignoring vulns.
        
       | rkrbaccord94f wrote:
       | The pipewire-libs package local address function refers to
       | alsa_output.pci
       | 
       | Driver benchmarking the pipewire script calls three local ports:
       | 
       | local.source.port = 10001
       | 
       | local.repair.port = 10002
       | 
       | local.control.port = 10003
        
       | samuelknight wrote:
       | LLMs are expert hackers because: 1) They are expert coders,
       | including a decently comprehensive CVE knowledge 2) They know
       | every programming language/framework/stack 3) They know every
       | human language
       | 
       | They already have super human breadth and attention. And their
       | depth is either super human or getting there.
       | 
       | The state of the security industry through 2025 was expensive
       | appsec human reviewers or primitive scanners. Now you can spend a
       | few dollars and have an expert intelligence scrutinize a whole
       | network.
        
         | gdulli wrote:
         | So much of the current internet is posts that read as a
         | superposition of sincere and parody, and until that's resolved
         | how do you know how to respond?
        
           | saltcured wrote:
           | Just wait until you see the same showing up in compliance
           | realms...
           | 
           | Edit: to be slightly less implicit, consider the cargo cult
           | madness that erupts from people thinking they can address
           | risk management and compliance by auto-generating
           | documentation and avoid really doing the legwork.
        
           | samuelknight wrote:
           | If that was a jab it my writing then yes, I am absolutely
           | being sincere because I am an expert on this topic. LLMs went
           | from being ok at one-shoting a function a to being so good at
           | hacking that it's difficult to evaluate them. Prospective
           | customers get back to us after a demo and tell us about the
           | exploits it found on their services that are so vague and
           | technical that they wouldn't think to look for them.
        
       | vibe42 wrote:
       | If everyone is running the same models, does this not favour
       | white hat / defense?
       | 
       | Since many exploits consists of several vulnerabilities used in a
       | chain, if a LLM finds one in the middle and it's fixed, that can
       | change a zero day to something of more moderate severity?
       | 
       | E.g. someone finds a zero day that's using three vulns through
       | different layers. The first and third are super hard to find, but
       | the second is of moderate difficulty.
       | 
       | Automated checks by not even SOTA models could very well find the
       | moderate difficulty vuln in the middle, breaking the chain.
        
       | anematode wrote:
       | Ya, I tend to believe that (most) human VR will be obsoleted well
       | before human software engineering. Software engineering is a lot
       | more squishy and has many more opportunities to go off the rails.
       | Once a goal is established, the output of VR agents is
       | verifiable.
        
       | GTP wrote:
       | > The new models find real stuff. Forget the slop; will projects
       | be able to keep up with a steady feed of verified, reproducible,
       | reliably-exploitable sev:hi vulnerabilities?
       | 
       | If LLMs are as capable as said in the article, there will be an
       | initial wave of security vulnerabilities. But then, all
       | vulnerabilities will be discovered (or at least, LLMs will not
       | find any more), and only new code will introduce new
       | vulnerabilities. And everyone will be using LLMs to check the new
       | code. So, regardless of what they say is correct or not, the
       | problem doesn't really exist.
        
       | m132 wrote:
       | A hard read for a skeptic like me. A lot of speculation and
       | extrapolation of a trend, not to say outright exaggeration, but
       | very little actual data. Let's not forget that we're at the tip
       | of an economic bubble, and what you're writing about is at the
       | very center of it!
       | 
       | For what it's worth, I read Anthropic's write-up of their recent
       | 0-day hunt that most of this post seems to be based on, and I
       | can't help but notice that (assuming the documented cases were
       | the most "spectacular") their current models mostly "pattern-
       | matched" their ways towards the exploits; in all documented
       | cases, the actual code analysis failed and the agents redeemed
       | themselves by looking for known-vulnerable patterns they
       | extracted from the change history or common language pitfalls.
       | So, most of the findings, if not all, were results of rescanning
       | the entire codebase for prior art. The corporate approach to
       | security, just a little more automated.
       | 
       | Hence I agree with "the smartest vulnerability researcher"
       | mentioned near the end. Yes, the most impactful vulnerabilities
       | tend to be the boring ones, and catching those fast will make a
       | big difference, but vulnerability research is far from cooked. If
       | anything, it will get much more interesting.
        
       | miki123211 wrote:
       | I think our saving grace is the fact that, especially in these
       | hardened environments, it's a lot easier to find exploitable bugs
       | than to actually exploit them.
       | 
       | As the defenders will have access to the same agents as the
       | attackers, everybody will (mostly) find the same bugs. If recent
       | trends continue[1], it's likely that major labs will make new
       | models available to defenders first, making the attackers' jobs
       | even harder.
       | 
       | What really worries me is models quickly developing exploits
       | based on freshly-released patches, before most people had a
       | chance to update. Big cloud vendors will likely have the ability
       | to coordinate and deploy updates before the commits hit Github,
       | smaller enterprise on-prem environments won't have that luxury.
        
       ___________________________________________________________________
       (page generated 2026-03-30 23:01 UTC)