URI:
        _______               __                   _______
       |   |   |.---.-..----.|  |--..-----..----. |    |  |.-----..--.--.--..-----.
       |       ||  _  ||  __||    < |  -__||   _| |       ||  -__||  |  |  ||__ --|
       |___|___||___._||____||__|__||_____||__|   |__|____||_____||________||_____|
                                                             on Gopher (inofficial)
  HTML Visit Hacker News on the Web
       
       
       COMMENT PAGE FOR:
  HTML   I think they are lying to you [video]
       
       
        mikgp wrote 10 hours 31 min ago:
        The one thing that gets me is - Boris must know what everyone is
        thinking when he says he merges 300 MR’s per day, but I think
        everyone knows it doesn’t mean what he’s implying - it just
        can’t.  He can’t read 300 open source contributions per day to
        determine if they fit into the spirit of Claude Code.  Even if he’d
        fully automated the testing and integration process.  And 300 people
        per day submitting contributions?
        
        He could mean a few other thingsc one would be, he has like 20 version
        tags and he merges 15 features into each version (does he explicitly
        say merge to main?)
        
        The other thing he could mean is he has like a software engineering
        agent and that software engineering agent like loops through GitHub
        issues and his personal notepad and maybe uses a few different branches
        to test things out and build I dunno adversarially, running all sorts
        of experiments.
        
        Which would be genuinely cool!    But using Mr’s to say tweak bunch of
        variables back and forth isn’t what 300 MR’s implies.
        
        But then the ultimate question is - it may be cool to fully automate a
        software engineering agent, and certainly is the type of research
        Anthropic and someone of Boris’ stature (and pay level) should be
        working on.  But is it efficient?
        
        I guess yes hems talked about this:
        
  HTML  [1]: https://karozieminski.substack.com/p/boris-cherny-claude-code-...
       
        nhinck2 wrote 10 hours 57 min ago:
        I mean you can go through Boris' history here on hn to see he is a
        liar.
       
        orangebread wrote 11 hours 30 min ago:
        I think this guy is using AI differently than me. Since Opus 4.6 and
        GPT 5.3, I have been able to absolutely crush my coding work. Boris
        might be embellishing how he ONLY writes loops, but for the most part I
        am just handing off planning docs to Claude or GPT and they implement
        it with like 95% accuracy.
        
        A lot of you don't want to hear it but this is a user issue.
       
          orangebread wrote 16 min ago:
          Wow, I did not expect this much response from my comment. First, let
          me say I am not flexing. I am very willing and happy to share HOW I'm
          able to achieve high quality code through my workflows and what my
          loops look like.
          
          I am currently building 4 projects at the same time using a
          boilerplate I developed for my own projects.
          
          One thing many people who are new to agentic coding harnesses may be
          missing is that a lot of workflows are personal to how the developer
          approaches design and implementation. So if you message me, please
          keep in mind that my approach may not align with how you approach
          software development.
          
          That said, I will do my best to abstract my process so it's
          applicable for your work. I would also recommend reading OpenAI's
          article on harness engineering: [1] DMs are open if you genuinely
          want to know how I work :)
          
          DISCORD: jayeeeffeff
          
  HTML    [1]: https://openai.com/index/harness-engineering/
       
          Jeremy1026 wrote 10 hours 3 min ago:
          This guy has been against AI from the very onset, and no matter what
          happens with AI going forward I think he'll always poopoo it.
       
            thraway3837 wrote 6 hours 37 min ago:
            This is the correct take. People who are closed minded and against
            this tool will always be against it, because they feel or think AI
            coding is an existential threat to them. If you think AI coding is
            going to replace your job, well, perhaps your job was just not all
            that important in the first place.
            
            Sorry that sucks to hear, but the real talent lies in systems
            thinking. How to make things look good. How to make it usable for
            humans. How to make something exciting and remove the blocker that
            was programming effort. Everything else is still a hard problem.
            And those are all people problems. Just because computers can now
            spit out computer code doesn't mean all the problems are solved.
            
            Case in point: As I comment on this article. The US govt has asked
            Claude to stop the export of the latest Fabel and Mythos models.
            And Anthropic decided it was just easier to disable those models
            for all users.
            
            These things aren't simple decisions. And we're just barely getting
            started with AI coding. Can't wait for what 1 year from now looks
            like :)
       
          ryan_n wrote 10 hours 4 min ago:
          > A lot of you don't want to hear it but this is a user issue.
          
          Hmm people say this all the time in these discussions but idk if I
          buy that it's really a "user issue". It's really, really not hard to
          "use" agentic ai. It literally involves instructing an llm to do
          things in natural language. Anyone who knows how to code and speak a
          language can do this. As you yourself seem to believe, even people
          who don't know how to code can do this. I just don't think it's
          possible that THAT many people are having an issue typing some words
          to instruct an llm to write some code. Maybe the issue is more the
          type of software you are working on vs the type of software that
          other people are working on. I don't know, I just don't think "skill
          issue" is really a valid argument here...
          
          Edit: for the record, I think what Opus can produce is extremely
          impressive. But I still am not really close to letting write 100% of
          code I write. And I think that is true for a lot of people, not just
          me. It still generates (sometimes obvious) bugs. Until that stops,
          the statement "coding is solved" is objectively false, which (I
          think?) is largely the point of the video.
       
            fragmede wrote 7 hours 49 min ago:
            you aren't, but there are other people out there that are having
            their agent write 100% of the code. Yes, there's a lot of people
            that aren't but also there are a lot of people that are. I don't
            think we can get an objective answer. I know we want cold hard
            facts, but turns out software in the real world contains more
            reading of star charts and tea leaves than we'd care to admit.
       
          triyambakam wrote 10 hours 15 min ago:
          I am definitely hyped on it and have 10-20 Codex and Claude Code
          terminals open, but I do wonder what you're building and with who
          that you would say 95% accuracy. I get so frustrated with Codex
          inventing new ways to do something every time it compacts or start a
          new session.
          
          "You're right, I shouldn't have done that" Ya think?!
       
          slopinthebag wrote 10 hours 27 min ago:
          If Anthropic has some of the best and most highly paid software
          engineers on the planet working on a simple program (terminal app)
          with virtually unlimited tokens for the strongest coding model, and
          they still ship a sloppy buggy mess, what does that say about the
          quality of code you are outputting?
          
          A lot of you don't want to hear it, but you aren't doing better than
          Anthropic so unless your use case is ridiculously simple, Claude Code
          is the ceiling for what you're creating, and if what you're doing is
          at all complex, the ceiling is much much lower.
       
          mikgp wrote 10 hours 41 min ago:
          You have planning docs?
          
          I am in no way surprised a sufficient waterfall method passed to
          Claude code could result in a completely accurate application.     But
          most applications aren’t built via waterfall for all the reasons.
          
          Also agents are just loops.  So if you use Claude Code you are doing.
          Everything with a loop.  So I do believe him but Im not entirely
          grokking the flex.
       
          reinitctxoffset wrote 10 hours 41 min ago:
          I read this a lot and it is just very foreign to me. I use AI systems
          in software work all day seven days a week and my job has become
          simultaneously more interesting and more difficult because I scale
          the ambition up until it's hard again.
          
          Isn't anything else a surrender to irrelevance? I agree that many
          coding tasks that were previously effort intensive are now not effort
          intensive, but there's no ceiling I'm aware of on how correct and
          performant and economical and capable software can be short of
          saturating the hardware.
          
          And the emergence of agentic intelligence at scale demands new
          regimes of performance and correctness and economy like maybe nothing
          else ever has.
          
          I have an anecdote related to TUI flickering in that my TUI library
          had a flickering problem because it was doing more than 10k FPS, and
          so I had to lock the buffer swap to the vsync to stop it tearing.
          
          AI coding didn't make more React too cheap to meter, it made
          notcurses bound into Trinity-inspired deterministic replay event
          substrate over io_uring possible.
          
  HTML    [1]: https://youtu.be/YqgEtpJ8tGI?feature=shared
       
          themafia wrote 10 hours 45 min ago:
          > just handing off planning docs to Claude or GPT and they implement
          it with like 95% accuracy.
          
          Do you have any publicly available demonstrations of this claim?
          
          > A lot of you don't want to hear it
          
          That there are skill differences in the use of technology?  On the
          contrary this knowledge makes me suspicious of undocumented claims
          like yours.
          
          > this is a user issue.
          
          Another claim I wish was quantified.  With all the billions invested
          I assumed this would naturally come to exist.  I may have just missed
          it.  Any pointers?
       
            calvinmorrison wrote 10 hours 40 min ago:
            > Do you have any publicly available demonstrations of this claim?
            
            Yeah I mean for example I wrote up a new audio mixer application
            for TDE using basically claude and just saying - hey rewrite the
            old ALSA one with Pulse/Pipewire.... its awesome. I dont know how
            it works.,
       
          taurath wrote 10 hours 50 min ago:
          Sorry, but context rot is real, and I’d be curious how your code is
          playing out in the real world. Is it shipping? Is it a known product
          with stable docs? Is it greenfield?
          
          Aspects of coding are faster certainly, but oh gosh can it get very
          wrong very fast when things go sideways, and with everyone using it,
          the chaos factor compounds into a near halt.
       
            dools wrote 10 hours 45 min ago:
            When you hand something off to Claude code, the harness is doing
            lots of different sessions it’s not a one shot.
       
          bag_boy wrote 11 hours 5 min ago:
          Can you give me your use case here? I have not gotten around to
          trying loops in Claude code but have started to notice the hype.
       
          nitwit005 wrote 11 hours 6 min ago:
          He's discussing Anthropic struggling to fix an issue with their own
          product. He's not the one struggling.
       
          thraway3837 wrote 11 hours 8 min ago:
          Yup. The only caveat I'd add is that I'm using an alternate account
          to agree with people who say that AI coding has been amazing, because
          there is a seemingly a good chunk of people who dislike it and it
          will be met with downvotes. Also because my real account has my real
          name in the profile along with projects I work on, and a simple
          search could reveal my pro-AI coding views and these same folks who
          downvote could also be a future interviewer.
          
          I think the world changed. And it's changed for the good. AI is a
          tool, and we should not be afraid of this tool for the coding world.
          I am only speaking about coding, I'm not speaking about other uses of
          AI, just so that we're clear on the scope of what I mean by good
          change.
          
          For the first time, I see people who had all these ideas finally
          bring them to reality and watch it blossom. They wanted to build
          something to share with their communities, but the walls were too
          high. Too much gatekeeping. Too much of thinking that programming was
          a task for the elite few and not for the masses. Along the way, we
          all forgot that we build tools for people. And having an additional
          tool help us make better tools for people is a win. Just below this
          comment, I see people talking about dementia, "lots more generated
          code, almost all of it garbage", "future where garbage software".
          
          I think the only delusional ones are the idea that humans were better
          at coding. Have you never had to work on an older project? One that
          you did not have to start fresh on? Or did you come into either one
          and go "wow, this is perfect! everything is so beautiful!" Do you
          seriously consider your fresh project (that didn't use AI) to be the
          best most perfect beautiful code ever?
          
          The fact is that nobody cares. People want to use good things and
          have fun with their lives. They're not worried about whether you
          wrote a method that parses some strings beautifully or did it with a
          one-liner. That never mattered, and I think a lot of you can't let go
          of that world view change and instead lash out at people who simply
          embrace that programming was simply a tool, not some elite special
          skill. And we're going back to those beliefs. It's done. It's over.
          Get over it.
       
            thraway3837 wrote 6 hours 36 min ago:
            And exactly as predicted: Downvoted to hell.
            
            Thanks, but the world's changed and there's no going back. Hope you
            can change with it.
       
            scooby7430 wrote 10 hours 36 min ago:
            Agreed. I think the opinion on AI is split into two camps, people
            who's enjoyment from programming came from writing the code and
            people who like building things. It's really undeniable at this
            point that AI has changed the job and I really enjoy it now more
            than ever, I can come up with an idea, guide an LLM through the
            steps to build it and have it be a real thing faster than I ever
            could have imagined.
            
            Yeah LLMs aren't perfect, there is back and forth along the way and
            if you just let it loose you are going to end up with slop but I
            feel like we can achieve better quality now in a shorter amount of
            time using the tool properly. I'm not sure if I am just naive but I
            am really excited about the possibilities now and have been
            spending more time than ever building what I want. I used to think
            that writing the code was the enjoyable part for me but I think it
            was just building things.
            
            I empathize with people in the other camp who got into it for the
            love of the code and now that part of the job is being taken away
            but I think it would benefit them to be honest about LLMs and try
            and work out a path forward here rather than just "my function is
            better than an LLM one, LLMs are just slop machines"
       
              thraway3837 wrote 6 hours 44 min ago:
              Great take and I agree
              
              Coding did have a certain amount of fun to it. When it was small.
              And needed to just do 1-2 things. Severely constrained in it's
              scope and impact. But, those were the QBasic days when I just
              made a cute app. That thinking has not scaled for applications of
              any size for decades now.
              
              I want to make great stuff for people and AI removes all the
              hurdles. Interviewing for asinine things like reversing a binary
              tree on the white board and then being nitpicked on getting the
              loop index wrong and then being ghosted is what the tech culture
              has devolved into. And its 100% caused by programmers who have
              grown too big of an ego and failed to develop socially.
              
              All of that is game over. It's done. In just under a year, the
              whole landscape has changed permanently. There are those that
              like help and create, and there are those that like to gatekeep
              simply because it makes them feel better. Nobody likes the
              latter.
       
            zingababba wrote 10 hours 56 min ago:
            Well said. Most of my career I made a trade-off and that trade-off
            was that I would much rather spend my free time outside in nature
            than on implementing my wild ideas which I always recognized would
            take considerable time. I'd maybe take 1% of my ideas anywhere. Now
            I can play with ideas while I'm out on the trail and turn those
            into something I can test within a couple hours, it's the most fun
            I've had on computers since the very beginning.
       
              thraway3837 wrote 10 hours 42 min ago:
              Very well said yourself! I frequently tell my friends (both in
              tech and polar opposite non-tech) that 3 things changed the tech
              world for me:
              
              1. Internet
              2. Smartphone
              3. AI coding
              
              All 3 were "WOW" moments for me.
       
        antonvs wrote 12 hours 0 min ago:
        It goes beyond lying. It's kind of war, and they're the aggressor.
        
        Everyone else needs to start treating them that way, or you're going to
        regret it once you realize what's actually happening.
       
          phendrenad2 wrote 11 hours 36 min ago:
          Please please tell us so we're prepared. sad puppy eyes
       
            antonvs wrote 9 hours 45 min ago:
            There's plenty of discussion of this if you look for it. Some
            examples:
            
            "Sanders Releases Report on Big Tech Oligarchs’ War Against
            Workers, Warns AI Could Eliminate Nearly 100 Million U.S. Jobs":
            [1] "How the American Oligarchy Went Hyperscale": [2] "AI Is a
            Threat to Everything the American People Hold Dear": [3] To be
            clear: I'm an extremely experienced software developer. I use AI
            daily. I'm currently working on training a DNN that's used in
            production by enterprise companies around the globe.
            
            But there's absolutely no doubt that AI is being deployed as a
            weapon by the capitalist class against everyone else, and that's
            only going to amplify and get much, much worse. The issue is not
            necessarily the technology itself. The issue is how society permits
            it to be used.
            
  HTML      [1]: https://www.help.senate.gov/dem/newsroom/press/news-sander...
  HTML      [2]: https://www.motherjones.com/politics/2026/04/american-olig...
  HTML      [3]: https://www.sanders.senate.gov/op-eds/ai-is-a-threat-to-ev...
       
              MAustriaGA wrote 5 hours 47 min ago:
              You lost me at “Sanders”
       
              phendrenad2 wrote 9 hours 18 min ago:
              What does this have to do with the video?
       
                antonvs wrote 7 hours 35 min ago:
                From 3m50s in the video:
                
                > I think they are lying, and I think they are hurting people.
                I think they're genuinely hurting people.
                
                That hurting of people is part of the war that I mentioned. The
                rest of the video focuses quite heavily on this general issue.
                It gives specific examples, but they're representative.
       
        bitwize wrote 12 hours 29 min ago:
        Pretty much the same point I made: [1] Their apparent inability to get
        the basics right makes me severely doubt their claims of self-improving
        AI. The humans at Anthropic wouldn't know improvement if it landed on
        their lap and started twerking, and AI cannot do a job without strong
        human intervention into what the goals and guardrails actually are.
        
        I'm kind of reminded of when Microsoft claimed it took a team of Ph.D.s
        to write a terminal application that updated at 60fps, and then Casey
        Muratori did it over a weekend. And this was before AI was writing code
        in earnest; when LLM-induced brainrot really sets in, civilization is
        in for a world of fresh hurt: lots more generated code, almost all of
        it garbage. And the promised AI crossover point where it becomes AGI,
        or indistinguishable from for software design purposes, recedes into
        the infinite future.
        
  HTML  [1]: https://news.ycombinator.com/item?id=48403908
       
          panarky wrote 11 hours 26 min ago:
          I watched the video and I wish I could get those 13 minutes of my
          life back.
          
          He could have done it in 13 seconds instead of 13 minutes: "Anthropic
          is lying about the effectiveness of agentic loops because there's
          this one screen flicker bug in Claude Code that took a year to fix."
          
          Yeah, like when United Airlines claims a plane can fly 300 people
          6,000 miles they are lying to you.
          
          I can prove they're lying to you because people have been complaining
          about uncomfortable seats and flight delays for literally decades and
          those issues still aren't fixed.
       
            theendisney wrote 10 hours 24 min ago:
            I write little bits of code then test them. If the screen flickers
            i wouldnt continue until it is solved. If ive missed it and have to
            hear it from (a) user(s) i would kinda like to fix it imediately.
            Not always possible but truly annoying things have priority over
            new things.
            
            If i had unlimited developers at my command. All many times as fast
            as me.... how can i keep the problem? It would take some huge
            effort to keep.
            
            The unlimited number of devs would talk about it an unlimited
            number of times. Not fixing it would be very expensive that way.
       
            Retric wrote 10 hours 50 min ago:
            He spent that much time and you still misunderstood the direct
            message and missed the subtext.
            
            The lie is coding is solved, the proof is they had an outstanding
            coding issue they were working on for over a year while saying
            coding is solved. There’s a great number of other issues with
            their own software that disprove their premise, but you only need
            one counter example to disprove something.
            
            And because you missed it, the subtext was they want you to use
            loops not because they work but because they burn lots of tokens
            thus making them more money.
       
              panarky wrote 10 hours 26 min ago:
              One unresolved bug does not disprove anything.
       
                Retric wrote 8 hours 47 min ago:
                A major outstanding software bug for a year proves they have
                not “solved coding,” which was their claim.
                
                I didn’t chose the words they used, but I can hold them to
                those words.
       
                ryan_n wrote 9 hours 59 min ago:
                The point is if "coding is solved" was true, there would not be
                any unresolved bugs.
       
                slopinthebag wrote 10 hours 21 min ago:
                And saying coding is solved doesn't prove anything either.
       
          rvz wrote 11 hours 41 min ago:
          > I'm kind of reminded of when Microsoft claimed it took a team of
          Ph.D.s to write a terminal application that updated at 60fps, and
          then Casey Muratori did it over a weekend.
          
          This is the same Microsoft that is now rewriting the TypeScript type
          checker, parser and its developer tools in Go after realizing that
          the bottleneck was...the performance of TypeScript itself, which is a
          basic compiled vs interpreted difference.
          
          > And this was before AI was writing code in earnest; when
          LLM-induced brainrot really sets in, civilization is in for a world
          of fresh hurt: lots more generated code, almost all of it garbage.
          
          Some folks using LLMs wouldn't realize why it makes zero sense to use
          TS / JS for building performant and optimal applications. This is why
          people were experiencing significant rendering bugs in terminal apps
          (they are not designed for that) and slow starts with Claude Code,
          which was completely vibe coded with Ink.
          
          If you don't understand the basic fundamentals of what you are
          working on with LLMs and bugs are creeping up left and right, then
          you are just sinking in your own comprehension debt.
       
          ai_slop_hater wrote 11 hours 50 min ago:
          Pretty much the same point I made
          
  HTML    [1]: https://news.ycombinator.com/item?id=48500537
       
          andrei_says_ wrote 11 hours 52 min ago:
          Reading this it occurs to me that this timeline may be moving toward
          a future where garbage software, garbage information etc. have become
          the norm for so long that the number of people who can distinguish
          trash from quality, or signal from noise, has become negligible.
          
          A true era of ignorance, looking like an ocean of nonsense in which
          no one can really navigate as it is ungrounded in reality.
          
          Idiocracy presents a naively gentle positive version of such future
          but there are many darker ones possible.
          
          Kali Yuga, indeed.
          
  HTML    [1]: https://en.wikipedia.org/wiki/Kali_Yuga
       
            ozgrakkurt wrote 4 hours 51 min ago:
            This is more because less educated people are coming onto the
            internet and programming.
            
            World was probably more ignorant before but internet/computers as a
            space was better because it consisted of a different set of people.
            
            There is still a ton of people that do understand quality and
            produce high quality stuff obviously
       
            slopinthebag wrote 10 hours 21 min ago:
            Perhaps, but people don't care that much about a bug with
            Instagram. Once critical infrastructure starts failing people will
            take notice.
       
            _doctor_love wrote 10 hours 53 min ago:
            The pralaya is not far away. Soon Shiva will begin his dance. I
            give us until 2036.
       
              kshri24 wrote 10 hours 40 min ago:
              Pralaya happens after complete age of Brahma. That would be 100
              Brahma years. Or 311.04 trillion human years. We are in the 51st
              year of Brahma.
              
              Kali Yuga lifespan is 432,000 years. Of which we are 4000+ years
              into it. So that's another 428,000 years of hell on Earth.
       
                triyambakam wrote 10 hours 14 min ago:
                Yeah like he said, not far away :D
       
            Retric wrote 10 hours 55 min ago:
            Customers abandon companies that fail.
            
            Remember how they used Brando to water plants and it kills them? 
            Eventually mistakes break critical systems and you fail.
       
            Papazsazsa wrote 11 hours 14 min ago:
            Ignorance is too generous a word. This is epistemic collapse.
       
          Jblx2 wrote 12 hours 4 min ago:
          "The Feeling of Power" by Arthur C. Clarke
       
            SpaceNoodled wrote 12 hours 0 min ago:
            Isaac Asimov, but yes.
       
              Jblx2 wrote 8 hours 54 min ago:
              argh
       
          wasabinator wrote 12 hours 17 min ago:
          Agreed. Watch for a rise in cases of early onset dementia over the
          next few decades.
       
            gdjdhdheb wrote 11 hours 58 min ago:
            No, we'll just find harder problems.... Coding is boring now
       
       
   DIR <- back to front page