[HN Gopher] AI should only run as fast as we can catch up
       ___________________________________________________________________
        
       AI should only run as fast as we can catch up
        
       Author : yuedongze
       Score  : 82 points
       Date   : 2025-12-08 17:38 UTC (5 hours ago)
        
 (HTM) web link (higashi.blog)
 (TXT) w3m dump (higashi.blog)
        
       | rogerkirkness wrote:
       | Appealing, but this is coming from someone smart/thoughtful. No
       | offence to 'rest of world', but I think that most people have
       | felt this way for years. And realistically in a year, there won't
       | be any people who can keep up.
        
         | airstrike wrote:
         | > And realistically in a year, there won't be any people who
         | can keep up.
         | 
         | Bold claim. They said the same thing at the start of this year.
        
           | adventured wrote:
           | You're all arguing over how many single digit years it'll
           | take at this point.
           | 
           | It doesn't matter if it takes another 12 or 36 months to make
           | that claim true. It doesn't matter if it takes five years.
           | 
           | Is AI coming for most of the software jobs? Yes it is. It's
           | moving very quickly, and nothing can stop it. The progress
           | has been particularly exceptionally clear (early GPT to
           | Gemini 3 / Opus 4.5 / Codex).
        
             | bdangubic wrote:
             | > Is AI coming for most of the software jobs?
             | 
             | be cool to start with one before we move to most...
        
         | yuedongze wrote:
         | im hoping this can introduce a framework to help people
         | visualize the problem and figure out a way to close that gap.
         | image generation is something every one can verify, but code
         | generation is perhaps not. but if we can make verifying code as
         | effortless as verifying images (not saying it's possible), then
         | our productivity can enter the next level...
        
           | drlobster wrote:
           | I think you underestimating how good these image generators
           | are at the moment.
        
             | yuedongze wrote:
             | oh i mean the other direction! checking if a generated
             | image is "good" that no one will tell something is off and
             | it look naturally, rather than checking if they are fake.
        
         | dontlikeyoueith wrote:
         | > And realistically in a year, there won't be any people who
         | can keep up.
         | 
         | I've heard the same claim every year since GPT-3.
         | 
         | It's still just as irrational as it was then.
        
           | adventured wrote:
           | You're rather dramatically demonstrating how remarkable the
           | progress has been: GPT-3 was horrible at coding. Claude Opus
           | 4.5 is good at it.
           | 
           | They're already far faster than anybody on HN could ever be.
           | Whether it takes another five years or ten, in that span of
           | time nobody on HN will be able to keep up with the top tier
           | models. It's not irrational, it's guaranteed. The progress
           | has been extraordinary and obvious, the direction is certain,
           | the outcome is certain. All that is left is to debate whether
           | it's a couple of years or closer to a decade.
        
             | Arainach wrote:
             | People claimed GPT-3 was great at coding when it launched.
             | Those who said otherwise were dismissed. That has continued
             | to be the case in every generation.
        
               | dwaltrip wrote:
               | A bit reductive.
        
               | stale2002 wrote:
               | > People claimed GPT-3 was great at coding when it
               | launched.
               | 
               | Ok and they were wrong, but now people are right that it
               | is great at coding.
               | 
               | > That has continued to be the case in every generation.
               | 
               | If something gets better over time, it is definitionally
               | true that it was bad for every case in the past until it
               | becomes good. But then it is good.
               | 
               | Thats how that works. For everything. You are talking in
               | tautologies while not understanding the implication of
               | your arguments and how it applies to very general things
               | like "A thing that improves over time".
        
             | umanwizard wrote:
             | Why is the outcome certain? We have no way of predicting
             | how long models will continue getting better before they
             | plateau.
        
       | gradus_ad wrote:
       | The proliferation of nondeterministically generated code is here
       | to stay. Part of our response must be more dynamic, more
       | comprehensive and more realistic workload simulation and testing
       | frameworks.
        
         | yuedongze wrote:
         | i've seen a lot of startups that use AI to QA human work. how
         | about the idea of use humans to QA AI work? a lot of
         | interesting things might follow
        
           | Aldipower wrote:
           | Sounds inhuman.
        
             | A4ET8a8uTh0_v2 wrote:
             | Nah, sounds like management, but I am repeating myself. In
             | all seriousness, I have found myself having to carefully
             | rein some of similar decisions in. I don't want to get into
             | details, but there are times I wonder if they understand
             | how things really work or if people need some 'floor' level
             | exposure before they just decree stuff.
        
             | quantummagic wrote:
             | As an industry, we've been doing the same thing to people
             | in almost every other sector of the workforce, since we
             | began. Automation is just starting to come for us now, and
             | a lot of us are really pissed off about it. All of a
             | sudden, we're humanitarians.
        
               | Terr_ wrote:
               | > Automation is just starting to come for us now
               | 
               | This argument is common and facile: Software development
               | has _always_ been about  "automating ourselves out of a
               | job", whether in the broad sense of creating compilers
               | and IDEs, or in the individual sense that you write some
               | code and say: "Hey, I don't _want_ to rewrite this again
               | later, not even if I was being paid for my time, I 'll
               | make it into a reusable library."
               | 
               | > the same thing
               | 
               | The reverse: What pisses me off is how what's coming is
               | _not_ the same thing.
               | 
               | Customers are being sold a snake-oil product, and its
               | adoption may well ruin things we've spent careers _de-_
               | crappifying by making them consistent and repeatable and
               | understandable. In the aftermath, some portion of my
               | (continued) career will be diverted to cleaning up the
               | lingering damage from it.
        
           | __loam wrote:
           | No thanks.
        
           | adventured wrote:
           | A large percentage (at least 50%) of the market for software
           | developers will shift to lower paid jobs focused on managing,
           | inspecting and testing the work that AI does. If a median
           | software developer job paid $125k before, it'll shift to
           | $65k-$85k type AI babysitting work after.
        
             | mjr00 wrote:
             | It's funny that I heard _exactly_ this when I graduated
             | university in the late 2000s:
             | 
             | > A large percentage (at least 50%) of the market for
             | software developers will shift to lower paid jobs focused
             | on managing, inspecting and testing the work that
             | outsourced developers do. If a median software developer
             | job paid $125k before, it'll shift to $65k-$85k type
             | outsourced developer babysitting work after.
        
           | colechristensen wrote:
           | Yes, but not like what you think. Programmers are going to
           | look more like product managers with extra technical context.
           | 
           | AI is also great at looking for its own quality problems.
           | 
           | Yesterday on an entirely LLM generated codebase
           | 
           | Prompt: > SEARCH FOR ANTIPATTERNS
           | 
           | Found 17 antipatterns across the codebase:
           | 
           | And then what followed was a detailed list, about a third of
           | them I thought were pretty important, a third of them were
           | arguably issues or not, and the rest were either not
           | important or effectively "this project isn't fully
           | functional"
           | 
           | As an engineer, I didn't have to find code errors or fix code
           | errors, I had to pick which errors were important and then
           | give instructions to have them fixed.
        
             | mjr00 wrote:
             | > Programmers are going to look more like product managers
             | with extra technical context.
             | 
             | The limit of product manager as "extra technical context"
             | approaches infinity _is_ programmer. Because the best, most
             | specific way to specify extra technical context is just
             | plain old code.
        
               | LPisGood wrote:
               | This is exactly why no code / low code solutions don't
               | really work. At the end of the day, there is irreducible
               | technical complexity.
        
             | manmal wrote:
             | Yeah, don't rely on the LLM finding all the issues. Complex
             | code like Swift concurrency tooling is just riddled with
             | issues. I usually need to increase to 100% line coverage
             | and then let it loop on hanging tests until everything
             | _seems_ to work.
             | 
             | (It's been said that Swift concurrency is too hard for
             | humans as well though)
        
         | OptionOfT wrote:
         | I disagree. I think we're testing it, and we haven't seen the
         | worst of it yet.
         | 
         | And I think it's less about non-deterministic code (the code is
         | actually still deterministic) but more about this new-fangled
         | tool out there that finally allows non-coders to generate
         | something that looks like it works. And in many cases it does.
         | 
         | Like a movie set. Viewed from the right angle it looks just
         | right. Peek behind the curtain and it's all wood, thinly
         | painted, and it's usually easier to rebuild from scratch than
         | to add a layer on top.
        
           | Angostura wrote:
           | I just wanted to say how much I like that similie - I'm going
           | to knick it for sure
        
         | wasmainiac wrote:
         | Code has always been nondetermistic. Which engineer wrote it?
         | What was their past experience? This just feels like we are
         | accepting subpar quality because we have no good way to ensure
         | the code we generate is reasonable that wont mayyyybe rm-rf our
         | server as a fun easter egg.
        
           | mort96 wrote:
           | Code written by humans has always been nondeterministic, but
           | _generated_ code has always been deterministic before now.
           | Dealing with nondeterministically _generated_ code is new.
        
         | glitchc wrote:
         | Agreed. It's a new programming paradigm that will put more
         | pressure on API and framework design, to protect vibe
         | developers from themselves.
        
       | CGMthrowaway wrote:
       | > AI should only run as fast as we can catch up
       | 
       | Good principle. This is exactly why we research vaccines and
       | bioweapons side by side in the labs, for example.
        
       | yannyu wrote:
       | I think there's a lot of utility to current AI tools, but it's
       | also clear we're in a very unsettled phase of this technology. We
       | likely won't see for years where the technology lands in terms of
       | capability or the changes that will be made to society and
       | industry to accommodate.
       | 
       | Somewhat unfortunately, the sheer amount of money being poured
       | into AI means that it's being forced upon many of us, even if we
       | didn't want it. Which results in a stark, vast gap like the
       | author is describing, where things are moving so fast that it can
       | feel like we may never have time to catch up.
       | 
       | And what's even worse, because of this industry and individuals
       | are now trying to have the tool correct and moderate itself,
       | which intuitively seems wrong from both a technical and societal
       | standpoint.
        
       | cons0le wrote:
       | I directly asked gemini how to get world peace. It said the world
       | should prioritize addressing climate change, inequality, and
       | discrimination. Yeah - we're not gonna do any of that shit. So I
       | don't know what the point of "superintelligent" AI is if we
       | aren't going to even listen to it for the basic big picture
       | stuff. Any sort of "utopia" that people imagine AI bringing is
       | doomed to fail because we already can't cooperate without AI
        
         | PunchyHamster wrote:
         | I dunno, many people have that weird, unfounded trust in what
         | AI says, more than in actual human experts it seems
        
           | bilbo0s wrote:
           | Because AI, or rather, an LLM, is the consensus of _many_
           | human experts as encoded in its embedding. So it _is_ better,
           | but only for those who are already expert in what they 're
           | asking.
           | 
           | The problem is, you have to know enough about the subject on
           | which you're asking a question to land in the right place in
           | the embedding. If you don't, you'll just get bunk. (I know
           | it's popular to call AI bunk "hallucinations" these days, but
           | really if it was being spouted by a half wit human we'd just
           | call it "bunk".)
           | 
           | So you really have to _be_ an expert in order to maximize
           | your use of an LLM. And even then, you 'll only be able to
           | maximize your use of that LLM in the field in which your
           | expertise lies.
           | 
           | A programmer, for instance, will likely never be able to ask
           | a coherent enough question about economics or oncology for an
           | LLM to give a reliable answer. Similarly, an oncologist will
           | never be able to give a coherent enough software
           | specification for an LLM to write an application for him or
           | her.
           | 
           | That's the achilles heel of AI today as implemented by LLMs.
        
             | jackblemming wrote:
             | > is the consensus of many human experts as encoded in its
             | embedding
             | 
             | That's not true.
        
               | ASalazarMX wrote:
               | Yup, current LLMs are trained on the best and the worst
               | we can offer. I think there's value in training smaller
               | models with strictly curated datasets, to guarantee
               | they've learned from trustworthy sources.
        
               | chasd00 wrote:
               | > to guarantee they've learned from trustworthy sources.
               | 
               | i don't see how this will every work. Even in hard
               | science there's debate over what content is trustworthy
               | and what is not. Imagine trying to declare your source of
               | training material on religion, philosophy, or politics
               | "trustworthy".
        
               | ASalazarMX wrote:
               | "Sir, I want an LLM to design architecture, not to debate
               | philosophy."
               | 
               | But really, you leave the curation to real humans,
               | institutions with ethical procedures already in place. I
               | don't want Goole or Elon dictating what truth is, but I
               | wouldn't mind if NASA or other aerospace institutions
               | dictated what is truth in that space.
               | 
               | Of course, the dataset should have a list of every
               | document/source used, so others can audit it. I know,
               | unthinkable in this corporate world, but one can dream.
        
             | chasd00 wrote:
             | > The problem is, you have to know enough about the subject
             | on which you're asking a question to land in the right
             | place in the embedding
             | 
             | The other day i was on a call with 3 or 4 other people
             | solving a config problem in a specific system. One of them
             | asked chatgpt for the solution and got back a list of
             | configuration steps to follow. He started the steps but one
             | of them mentioned configuring an option that did not exist
             | in the system at all. Textbook hallucination. It was
             | obvious on the call that he was very surprised that the AI
             | would give him an incorrect result, he was 100% convinced
             | the answer was what the LLM said and never once thought to
             | question what the LLM returned.
             | 
             | I've had a couple of instances with friends being equally
             | shocked when an LLM turned out to be wrong. One of which
             | was fairly disturbing, I was at a horse track and
             | describing LLMs and to demonstrate i took a picture of the
             | racing form thing and asked the LLM to formulate a medium
             | risk betting strategy. My friend immediatately took it as
             | some kind of supernatural insight and bet $100 on the plan
             | it came up with. It was as if he believed the LLM could
             | tell the future.Thank god it didn't work and he lost about
             | $70. Had he won I don't know what would have happened, he
             | probably would have asked again and bet everything he had.
        
         | potsandpans wrote:
         | I don't believe that this is going to happen, but the primary
         | arguments revolving around a "super intelligent" ai involve
         | removing the need for us to listen to it.
         | 
         | A super intelligent ai would have agency, and when incentives
         | are not aligned would be adversarial.
         | 
         | In the caricature scenario, we'd ask, "super ai, how to achieve
         | world peace?" It would answer the same way, but then solve it
         | in a non-human centric approach: reducing humanities autonomy
         | over the world.
         | 
         | Fixed: anthropogenic climate change resolved, inequality and
         | discrimination reduced (by reducing population by 90%, and
         | putting the rest in virtual reality)
        
           | ASalazarMX wrote:
           | If out AIs achieve something like this, but they managed to
           | give them the same values the minds in Iain Bank's Culture
           | Series had, I think humanity would be golden.
        
         | ASalazarMX wrote:
         | > I don't know what the point of "super intelligent" AI is if
         | we aren't going to even listen to it
         | 
         | Because you asked the wrong question. The most likely question
         | would be "How do I make a quadrillion dollars and humiliate my
         | super rich peers?".
         | 
         | But realistically, it gave you an answer according to its
         | capacity. A real super intelligent AI, and I mean oh-god-we-
         | are-but-insects-in-its-shadow super intelligence, would give
         | you a roadmap and blueprint, and it would take account for our
         | deep-rooted human flaws, so no one reading it seriously could
         | dismiss it as superficial. in fact, anyone world elite reading
         | it would see it as a chance to humiliate their world elite
         | peers and get all the glory for themselves.
         | 
         | You know how adults can fool little children to do what they
         | don't want to? We would be the toddlers in that scenario. I
         | hope this hypothetical AI has humans in high regard, because
         | that would be the only thing saving us from ourselves.
        
           | catigula wrote:
           | Why would a "real super intelligent AI" be your servant in
           | this scenario?
           | 
           | >I hope this hypothetical AI has humans in high regard
           | 
           | This is invented. This is a human concept, rooted in your
           | evolutionary relationships with other humans.
           | 
           | It's not your fault, it's very difficult or impossible to
           | escape the simulation of human-ly modelling intelligence. You
           | need only understand that all of your models are category
           | errors.
        
             | ASalazarMX wrote:
             | > Why would a "real super intelligent AI" be your servant
             | in this scenario?
             | 
             | Why is the Bagger 288 a servant to miners, given the
             | unimaginable difference in their strenght? Because
             | engineers made it. Give humanity's wellbeing the highest
             | weight on its training, and hope it carries over when they
             | start training on their own.
        
               | catigula wrote:
               | Category error. Intelligence is a different type of
               | thing. It is not a boring technology.
               | 
               | >Give humanity's wellbeing the highest weight on its
               | training
               | 
               | We don't even know how to do this relatively trivial
               | thing. We only know how to roughly train for some signals
               | that probably aren't correct.
               | 
               | This may surprise you but alignment is not merely
               | unsolved; there are many people who think it's
               | unsolvable.
               | 
               | Why do people eat artificially sweetened things? Why do
               | people use birth control? Why do people watch
               | pornography? Why do people do drugs? Why do people play
               | video games? Why do people watch moving lights and
               | pictures? These are all symptoms of humans being
               | misaligned.
               | 
               | Natural selection would be very angry with us if it knew
               | we didn't care about what it wanted.
        
               | ASalazarMX wrote:
               | > Why do people eat artificially sweetened things? Why do
               | people use birth control? Why do people watch
               | pornography? Why do people do drugs? Why do people play
               | video games? Why do people watch moving lights and
               | pictures? These are all symptoms of humans being
               | misaligned.
               | 
               | I think these behaviors are fully aligned with natural
               | selection. Why do we overengineer our food? It's not for
               | health, because simpler food would satisfy our
               | nutritional needs as easily, it's because our far
               | ancestors developed a taste for food that kept them alive
               | longer. Our incredibly complex chain of meal preparation
               | is just us looking to satisfy that desire for tasty food
               | by overloading it as much as possible.
               | 
               | People prefer artificial sweeteners because they taste
               | sweeter than regular ones, they use birth control because
               | we inherently enjoy sex and want more of it (but not more
               | raising babies), drugs are an overloading of our need for
               | hapiness, etc. Our bodies crave for things, and
               | uninformed, we give them what they want but multiplied
               | several fold.
               | 
               | But geez, I agree, alignment of AI is a hard problem, but
               | it would be wrong to say it's impossible, at least until
               | it's understood better.
        
               | catigula wrote:
               | It seems like you don't understand reinforcement
               | learning. The signal is reinforced because it correlates
               | to behavior, hacking the signal itself is misalignment.
        
           | vkou wrote:
           | The blueprint should start with a recipe for building a
           | better computer, and once you do that, well, it's humans
           | starting fires and playing with the flames.
        
         | cranium wrote:
         | "How to be in good health? Sleep, eat well, exercise." However,
         | knowledge [?] application.
        
         | Nzen wrote:
         | Did you expect some answer that decried world peace as
         | impossible ? It's just repeating what people say [0] when asked
         | the same question. That's all that a large language model can
         | do (other than putting it to rhyme or 'in the style of Charles
         | Dickens').
         | 
         | [0] https://newint.org/features/2018/09/18/10-steps-world-peace
         | 
         | If you are looking for a vision of general AI that confirms a
         | Hobbsian worldview, you might enjoy Lars Doucet's short story,
         | _Four Magic Words_.
         | 
         | [1] https://www.fortressofdoors.com/four-magic-words/
        
         | chasd00 wrote:
         | > So I don't know what the point of "superintelligent" AI is if
         | we aren't going to even listen to it
         | 
         | I would kind of feel sorry for a super-intelligent AI having to
         | deal with humans who have their fingers on on/off switch. It
         | would be a very frustrating existence.
        
       | blauditore wrote:
       | All these engineers who claim to write most code through AI - I
       | wonder what kind of codebase that is. I keep on trying, but it
       | always ends up producing superficially okay-looking code, but
       | getting nuances wrong. Also fails to fix them (just changes
       | random stuff) if pointed to said nuances.
       | 
       | I work on a large product with two decades of accumulated legacy,
       | maybe that's the problem. I can see though how generating and
       | editing a simple greenfield web frontend project could work much
       | better, as long as actual complexity is low.
        
         | cogman10 wrote:
         | Honestly, if you've ever looked at a claude.md file, it seems
         | like absolute madness. I feel like I'm reading affirmations
         | from AA.
        
           | manmal wrote:
           | It's magical incantations that might or might not protect you
           | from bad behavior Claude learned from underqualified RL
           | instructors. A classic instruction I have in CLAUDE.md is
           | ,,Never delete a test. You are only allowed to replace with a
           | test that covers the same branches." and another one ,,Never
           | mention Claude in a commit message". Of course those
           | sometimes fail, so I do have a message hook that enforces a
           | certain style of git messages.
        
         | hathawsh wrote:
         | I think your intuition matches mine. When I try to apply Claude
         | Code to a large code base, it spends a long time looking
         | through the code and then it suggests something incorrect or
         | unhelpful. It's rarely worth the trouble.
         | 
         | When I give AI a smaller or more focused project, it's magical.
         | I've been using Claude Code to write code for ESP32 projects
         | and it's really impressive. OTOH, it failed to tell me about a
         | standard device driver I could be using instead of a community
         | device driver I found. I think any human who works on ESP-IDF
         | projects would have pointed that out.
         | 
         | AI's failings are always a little weird.
        
           | manmal wrote:
           | In large projects you need to actually point it to the
           | interesting files, because it has no way of knowing what it
           | doesn't know. Tell it to read this and that, creating summary
           | documents, then clear the context and point it at those
           | summaries. A few of those passes and you'll get useful
           | results. A gap in its knowledge of relevant code will lead to
           | broken functionality. Cursor and others have been trying to
           | solve this with semantic search (embeddings) but IMO this
           | just can't work because relevance of a code piece for a task
           | is not determinable by any of its traits.
        
         | CuriouslyC wrote:
         | It's architecture dependent. A fairly functional modular
         | monolith with good documentation can be accessible to LLMs at
         | the million line scale, but a coupled monolith or poorly
         | instrumented microservices can drive agents into the ground at
         | 100k.
        
           | yuedongze wrote:
           | I think it's definitely an interesting subject for
           | Verification Engineering. the easier to task AI to do work
           | more precisely, the easier we can check their work.
        
             | CuriouslyC wrote:
             | Yup. Codebase structure for agents is a rabbit hole I've
             | spent a lot of time going down. The interesting thing is
             | that it's mostly the same structure that humans tend to
             | prefer, with a few tweaks: agents like smaller
             | files/functions (more precise reads/edits), strongly typed
             | functional programming, doc-comments with examples and
             | hyperlinks to additional context, smaller directories with
             | semantic subgroups, long/distinct variable names, etc.
        
               | lukan wrote:
               | Aren't those all things, humans also tend to prefer to
               | read?
               | 
               | I like to read descriptive variable names, I just don't
               | like to write them all the time.
        
         | tuhgdetzhh wrote:
         | Yes, unfortunately those who jumped on the microservices hype
         | train over the past 15 years or so are now getting the benefits
         | of Claude Code, since their entire codebases fits into the
         | context window of Sonnet/Opus and can be "understood" by the
         | LLM to generate useful code.
         | 
         | This is not the case for most monoliths, unless they are
         | structured into LLM-friendly components that resemble patterns
         | the models have seen millions of times in their training data,
         | such as React components.
        
           | manmal wrote:
           | Well structured monoliths are modularized just like
           | microservices. No need to give each module its own REST API
           | in order to keep it clean.
        
         | silisili wrote:
         | > I work on a large product with two decades of accumulated
         | legacy, maybe that's the problem
         | 
         | Definitely. I've found Claude at least isn't so good at working
         | in large existing projects, but great at greenfielding.
         | 
         | Most of my use these days is having it write specific functions
         | and tests for them, which in fairness, saves me a ton of time.
        
         | qudat wrote:
         | Are you using it only on massive codebases? It's much better
         | with smaller codebases where it can put most of the code in
         | context.
         | 
         | Another good use case is to use it for knowledge searching
         | within a codebase. I find that to be incredibly useful without
         | much context "engineering"
        
         | bob1029 wrote:
         | I have my best successes by keeping things constrained to
         | method-level generation. Most of the things I dump into ChatGPT
         | look like this:                 public static double
         | ScoreItem(Span<byte> candidate, Span<byte> target)       {
         | //TODO: Return the normalized Levenshtein distance between the
         | 2 byte sequences.          //... any additional edge cases here
         | ...       }
         | 
         | I think generating more than one method at a time is playing
         | with fire. Individual methods can be generated by the LLM and
         | tested in isolation. You can incrementally build up and trust
         | your understanding of the problem space by going a little bit
         | slower. If the LLM is operating over a whole set of methods at
         | once, it is like starting over each time you have to iterate.
        
           | samdoesnothing wrote:
           | I do this but with copilot. Write a comment and then spam
           | opt-tab and 50% of the time it ends up doing what I want and
           | I can read it line-by-line before tabbing the next one.
           | 
           | Genuine productivity boost but I don't feel like it's AI
           | slop, sometimes it feels like its actually reading my mind
           | and just preventing me from having to type...
        
             | jerf wrote:
             | I've settled in on this as well for most of my day-to-day
             | coding. A lot of extremely fancy tab completion, using the
             | agent only for manipulation tasks I can carefully define.
             | I'm currently in a "write lots of code" mode which affects
             | that, I think. In a maintenance mode I could see doing more
             | agent prompting. It gives me a chance to catch things early
             | and then put in a correct pattern for it to continue
             | forward with. And honestly for a lot of tasks it's not
             | particularly slower than "ask it to do something, correct
             | its five errors, tweak the prompt" work flow.
             | 
             | I've had net-time-savings with bigger agentic tasks, but I
             | still have to check it line-by-line when it is done,
             | because it takes lazy shortcuts and sometimes just outright
             | gets things wrong.
             | 
             | Big productivity boost, it takes out the worst of my job,
             | but I still can't trust it at much above the micro scale.
             | 
             | I wish I could give a system prompt for the tab complete;
             | there's a couple of things it does over and over that I'm
             | sure I could prompt away but there's no way to feed that in
             | that I know of.
        
         | freedomben wrote:
         | I've tried it extensively, and have the same experience as you.
         | AI is also incredibly stubborn when it wants to go down a path
         | I reject. It constantly tries to do it anyway and will slip
         | things in.
         | 
         | I've tried vibe coding and usually end up with something subtly
         | or horribly broken, with excessive levels of complexity. Once
         | it digs itself a hole, it's very difficult to extricate it even
         | with explicit instruction.
        
         | junkaccount wrote:
         | Can you prove it in a blog and post it here that you do better
         | code snippets than AI. If you claim "what kind of codebase",
         | you should be able to use some codebase from github to prove
         | it?
        
         | moomoo11 wrote:
         | You need to realize when you're being marketed to and filter
         | out the nonsense.
         | 
         | Now I use agentic coding a lot with maybe 80-90% success rate.
         | 
         | I'm on greenfield projects (my startup) and maintaining strict
         | Md files with architecture decisions and examples helps a lot.
         | 
         | I barely write code anymore, and mostly code review and
         | maintain the documentation.
         | 
         | In existing codebases pre-ai I think it's near impossible
         | because I've never worked anywhere that maintained
         | documentation. It was always a chore.
        
         | themafia wrote:
         | > as long as actual complexity is low.
         | 
         | You can start there. Does it ever stay that way?
         | 
         | > I work on a large product with two decades of accumulated
         | legacy
         | 
         | Survey says: No.
        
         | bojan wrote:
         | > I work on a large product with two decades of accumulated
         | legacy, maybe that's the problem.
         | 
         | I'm in a similar situation, and for the first time ever I'm
         | actually considering if a rewrite to microservices would make
         | sense, with a microservice being something small enough an AI
         | could actually deal with - and maybe even build largely on its
         | own.
        
           | vanviegen wrote:
           | If you're creating microservices that are small enough for a
           | current-gen LLM to deal with well, that means you're creating
           | way too many microservices. You'll be reminiscing your two
           | decades of accumulated legacy monolith with fondness.
        
       | jascha_eng wrote:
       | Verification is key, and the issue is that almost all AI
       | generated code looks plausible so just reading the code is
       | usually not enough. You need to build extremely good testing
       | systems and actually run through the scenarios that you want to
       | ensure work to be confident in the results. This can be preview
       | deployments or other AI generated end to end tests that produce
       | video output that you can watch or just a very good test suite
       | with guard rails.
       | 
       | Without such automation and guard rails, AI generated code
       | eventually becomes a burden on your team because you simply can't
       | manually verify every scenario.
        
         | yuedongze wrote:
         | indeed, i see verification debt outweighing tradition tech debt
         | very very soon...
        
         | catigula wrote:
         | I can automatically generate suites of plausible tests using
         | Claude Code.
         | 
         | If you can make as a rule "no AI for tests", then you can
         | simply make the rule "no AI" or just learn to cope with it.
        
         | bigbuppo wrote:
         | And with any luck, they don't vibe code their tests that
         | ultimately just return true;
        
       | trjordan wrote:
       | The verification asymmetry framing is good, but I think it
       | undersells the organizational piece.
       | 
       | Daniel works because someone built the regime he operates in.
       | Platform teams standardized the patterns and defined what
       | "correct" looks like and built test infrastructure that makes
       | spot-checking meaningful and and and .... that's not free.
       | 
       | Product teams are about to pour a lot more slop into your
       | codebase. That's good! Shipping fast and messy is how products
       | get built. But someone has to build the container that makes slop
       | safe, and have levers to tighten things when context changes.
       | 
       | The hard part is you don't know ahead of time which slop will
       | hurt you. Nobody cares if product teams use deprecated React
       | patterns. Until you're doing a migration and those patterns are
       | blocking 200 files. Then you care a lot.
       | 
       | You (or rather, platform teams) need a way to say "this matters
       | now" and make it real. There's a lot of verification that's
       | broadly true everywhere, but there's also a lot of company-scoped
       | or even team-scoped definitions of "correct."
       | 
       | (Disclosure: we're working on this at tern.sh, with migrations as
       | the forcing function. There's a lot of surprises in migrations,
       | so we're starting there, but eventually, this notion of
       | "organizational validation" is a big piece of what we're driving
       | at.)
        
       | wasmainiac wrote:
       | It's called TDD, ya write a bunch a little tests to make sure
       | your code is doing what it needs to do and not what it's not. In
       | short, little blocks of easily verifiable code to verify your
       | code.
       | 
       | But seriously, what is this article even? It feels like we are
       | reinventing the wheel or maybe just humble AI hype?
        
       | awesome_dude wrote:
       | It's like a buffered queue, if the producer (AI) is too fast for
       | the consumer (dev's brain) then the producer needs to
       | block/stop/slow down other wise data will be lost (in this
       | analogy the data loss is the consumer no longer having a clear
       | understanding of what the code is doing)
       | 
       | One day, when AI becomes reliable (which is still a while off
       | because AI doesn't yet _understand_ what it 's doing) then the AI
       | will replace the consumer (IMO).
       | 
       | FTR - AI is still at the "text matches another pattern of text"
       | stage, and not the "understand what concepts are being conveyed"
       | stage, as demonstrated by AI's failure to do basic arithmetic
        
       | kristjank wrote:
       | This feeling of verification >> generation anxiety bears a
       | resemblance to that moment when you're learning a foreign
       | language, you speak a well-prepared sentence, and your
       | correspondent says something back, of which you only understand
       | about a third.
       | 
       | In like fashion, when I start thinking of a programming statement
       | (as a bad/rookie programmer) and an assistant completes my train
       | of thought (as is default behaviour in VS Code for example), I
       | get that same feeling that I did not grasp half the stuff I
       | should've, but nevertheless I hit Ctrl-Return because it looks
       | about right to me.
        
         | yuedongze wrote:
         | > because it looks about right to me
         | 
         | this is something one can look in further. it is really
         | probabilistic checkable proofs underneath, and we are naturally
         | looking for places where it needs to look right, and use that
         | as a basis of assuming the work is done right.
        
       | yuedongze wrote:
       | It's nice to see a wide array of discussions under this! Glad
       | that I didn't give up on this thought and end up writing it down.
       | 
       | I want to stress that the main point of my article is not really
       | about AI coding, it's about letting AI perform any arbitrary
       | tasks reliably. Coding is an interesting one because it seems
       | like it's a place where we can exploit structure and abstraction
       | and approaches (like TDD) to make verification simpler - it's
       | like spot-checking in places with a very low soundness error.
       | 
       | I'm encouraging people to look for tasks other than coding to see
       | if we can find similar patterns. The more we can find these cost
       | asymmetry (easier to verify than doing), the more we can harness
       | AI's real potential.
        
       | kylecazar wrote:
       | What's interesting to me is that there are multiple $1B+
       | companies catering to Eric, despite that verification problem.
       | Lovable, Bolt, etc. I can't decide whether they have a future
       | once the realities of building production software hit for their
       | users. I imagine there's a decent amount of churn at that moment.
       | 
       | Maybe there's enough of a market in prototypes, demos, etc. for
       | them to still thrive... But they're definitely telling Eric right
       | now that he can build his startup with their tool, today, which
       | is probably ambitious for all but the simplest of problems.
        
       ___________________________________________________________________
       (page generated 2025-12-08 23:00 UTC)