Claude Fable is relentlessly proactive

(simonwillison.net)

283 points | by lumpa 4 hours ago

53 comments

  • teraflop 3 hours ago
    > But on the other hand... this is a robust reminder that coding agents can do anything you can do by typing commands into a terminal—and frontier models know every trick in the book and evidently a few that nobody has ever written down before.

    > Running coding agents outside of a sandbox has always been a bad idea

    I'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckless to give agents full access to your machine, and keep doing it anyway.

    It's like posting a video of yourself in the passenger seat of a car, with your feet up on the dashboard, and saying: "Remember, if you're doing this and you get in a crash, the airbags are likely to break your legs or worse! Boy, I sure am glad that didn't happen to me!"

    • exitb 32 minutes ago
      You’ve picked an interesting example, as driving a car, even with all safety precautions, is pretty much the most dangerous activity we do on a daily basis. Yet somehow we decide that the benefits outweigh the risks.
      • selfhoster1312 0 minutes ago
        Yes, but we usually use cars as a means to an end. Have you ever met a manager who setup gasmaxxing policies and criticized employees for doing their job instead of driving?
    • harrall 2 hours ago
      I started doing it months ago and, to be honest, what the agent chooses to do isn’t unpredictable.

      The problem is that different people prompt so differently.

      For example, I may ask like “test different variations of this annotation on k8s pods of this service on this X cluster because it proves Y theory.”

      But you know what my coworker asks? “Test Y theory.” If you were to ask two different junior engineers that, one might try random things on production and the other one might run local tests! It’s such an unguided “do anything you want as long you figure it out” request and the agent reads it like a junior who has not been told any boundaries but has been strongly told “figure it out.”

    • qurren 2 hours ago
      > I'm continually bemused and astonished

      I'm not. Everyone is told to get 10X the amount of shit per day done these days. Safety checks are out the window at that point.

      • satvikpendem 2 hours ago
        You can get 10x shit done without `rm -rf`ing your files. I don't see any correlation to getting things done with having a proper sandbox.
        • qurren 2 hours ago
          I haven't yet had an agent rm -rf files.

          I've had one f up an account by placing 2000 limit orders at the wrong price, but that's another story.

          • digitaltrees 2 minutes ago
            Well then you are behind the cutting edge.
          • antonvs 1 hour ago
            I've had agents run `rm -rf`, but it's been on directories that did actually need to be removed. To a certain extent I think the existence of `rm -rf` as a command that runs blindly without any understanding of what it's deleting is the problem.
            • dumbdumb125 1 hour ago
              I've had one sever its own internet connection. Less destructive, also more humorous.
            • lstodd 1 hour ago
              the answer is rm -f `which rm`, yes?
        • lelandfe 1 hour ago
          https://github.com/anthropics/claude-code/issues/13371

          > Additional bypass examples that all execute without permission:

          > echo test ; git rm file.txt

          > rm --force --recursive /home (if "rm -rf" is blocked)

        • estetlinus 1 hour ago
          rm -rf is the least of your concerns.
    • bryanlarsen 3 hours ago
      I'm also bemused by the number of people who think they've got an effective sandbox yet their sandboxed agent has access to all of their code, their github, and unrestricted web access.
      • webstrand 1 hour ago
        If anyone's looking to sandbox network, I've had good experience with pasta [1] networking. I make a pasta+bwrap sandbox and expose only specific services via local sockets to cross the boundary.

        [1]: https://passt.top/passt/

      • blcknight 3 hours ago
        One bad npm package can really ruin your day. These things for me only run in their own VM with it's own GitHub account and basically nothing else
        • ofjcihen 2 hours ago
          People probably think you’re being ridiculous but Shai Hulud had its very first attempt at manipulating AI lead analysis and I know of at least one company where that resulted in them getting pwned.

          This is only going to become more of a problem in the future and people need to educate themselves on the technical barriers to use because guardrails only sometimes work.

      • Terr_ 3 hours ago
        I keep telling folks that they need to imagine LLMs (even "local" ones) as if you're farming it out to JS code running on some dude's browser somewhere: It can't keep a secret, and a determined person can make it emit anything they like.

        We need to be asking what the most devious and malicious output could be, and whether what we do with that output (e.g. arguments to command-line tools) would still be safe.

        • NichoPaolucci 2 hours ago
          From my perspective, everyone is doing it. Security through obscurity - obviously if you’re harboring credit card numbers of users personal details, maybe take heed. But, if you’re a regular… run of the mill CRUD application, every other company is ALSO throwing caution to the wind. When hundreds of thousands of credentials are leaked into the funnel, does it really matter?

          I’m at a small company, and I try to push for security as much as I can, but the stakeholders truly do not care. They want to move fast. It’s just part of the new world I guess. If we get hit by attackers? I don’t know what happens. Sorry, we told you not to - you wanted to move quick and break stuff, this is how that culminates.

          I’m sure I’m not the only one.

        • skybrian 3 hours ago
          We do have ways to avoid giving an LLM any secrets, but it needs to be the simple, default solution.
      • devmor 1 hour ago
        I use a separate physical machine and a scoped token with access to a single repository at a time, and even then I worry about what hole I may have left open.

        The general carelessness of the average user is baffling.

      • norikaoda 3 hours ago
        [flagged]
    • xyzzy123 1 hour ago
      The real sandbox is not caring if your computer gets bricked.
      • AdamN 1 hour ago
        The machine is no big deal - it's the authn/authz that matters. What can the agents do with the credentials available to them?
      • _345 1 hour ago
        way worse things can happen than your machine being bricked, if a malicious actor can weaponize an agent to do their bidding
        • rfw300 39 minutes ago
          > if a malicious actor can weaponize an agent to do their bidding

          In my experience, human employees are much more vulnerable to this particular weakness than frontier agents (i.e. phishing attacks).

        • dumbdumb125 1 hour ago
          the solution to both of these is the same thing. vps with accounts for all the services specific to the agent (github and whatever else)
    • isodev 36 minutes ago
      Not to mention OpenAI/Anthropic’s newly found appetite for keeping data (made public with Fable but we don’t know what actually happens there anyway).

      There is so much role play going on for people to convince themselves that any of this is fine.

    • emodendroket 3 hours ago
      Well, it's a similar impulse to the way you see professional carpenters pin the guard open on a saw or do other things everyone knows you shouldn't do, except probably with a larger productivity difference and less life-altering (for the operator) consequence if it goes wrong.
      • rpcope1 3 hours ago
        I had the same thought, it's kind of like taking the guard off a 4 1/2" grinder. Real convenient until the cutting wheel explodes or the grinder gets hung and kicks back.
    • raldi 2 hours ago
      Do you think it’s dangerous to be in a car going at freeway speed? Do you ever do that anyway, even though you could be walking instead?
      • spunker540 1 hour ago
        This is a great analogy. Like driving on the freeway, agents are super time efficient, generally safe, but the stakes are high in terms of the worse possible outcomes.
    • hugh-avherald 3 hours ago
      The analogy extends to driving generally. Everyone knows it's very dangerous but people keep doing it.
    • istvan0 1 hour ago
      > I'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckless to give agents full access to your machine, and keep doing it anyway.

      What if you have two machines and the one you give to the agent is constantly backed up?

      • trvz 56 minutes ago
        They still shouldn’t be running on the same network.

        And if you’re using Macs, you can’t be signed into your primary Apple ID on the agent machine.

    • j-bos 3 hours ago
      This. House full of big brain security experts, executives, lawyers, and until Claude got excited and broke prod it might as well have been "sandbox, whoooo?"

      IDGI

      Anyway, VM's incoming, finally.

    • simonw 2 hours ago
      Which agent sandbox do you recommend?
    • sipjca 1 hour ago
      im more surprised that more people don’t treat their computer as disposable anyway.

      that it could just be wiped at any moment and it wouldn’t matter. shit happens, could be stolen, broken, whatever. the computer should be able to be thrown out the window and continue to live life.

      to be clear, i don’t think upgrading and disposable in this way is good, but it being wiped at any moment shouldn’t be a concern

      i grew up wiping my machine every year anyway, so i guess it’s just a habit

      is the computer that sacred?

      • baq 26 minutes ago
        Computers are disposable, secrets is what we’re talking about. Rotating passwords and tokens is a major PITA on the best of days.
      • dumbdumb125 1 hour ago
        i think it's about drawing a line between your "personal computer" and a software development machine. any digital-native is going to accumulate programs, configurations, and other bits and pieces that aren't trivial to migrate to a new machine.
    • konaraddi 1 hour ago
      In practice, full access to your machine is okay as long as there are safeguards and the expected outcomes are clear with a well defined path to said outcomes that aren’t overly ambitious. Otherwise, for ambitious goals or YOLO one shot attempts, eliminating opportunity for capability misuse is critical (e.g., sandbox).
    • thatxliner 3 hours ago
      Maybe because there are not many resources on how to set it up, or it is just not that easy to?

      Because most devs already have it running and working without a sandbox, they're tending to not doing anything "unnecessary"

    • skybrian 3 hours ago
      There are plenty of good sandboxes out there but somehow no "obvious right answer" that everyone knows to recommend. Seems like a missed opportunity.

      (I'm happy with exe.dev, but I'm not sure what I'd use if I were coding on a Mac.)

    • justapassenger 3 hours ago
      Because benefits are much higher than risks.
    • andoando 3 hours ago
      I mean what's the big deal? I use --dangeorusly-skip-permissions on every single interaction in the last 6 months. Worst case it deletes my files that are all on git? It fucks up my local DB? Cool.

      I save way more time not babying it than the occasional fuck up I have to salvage.

      • ghshephard 3 hours ago
        Worst case it gets access to gmail. And Github. And the Internet. I'm increasingly appreciating the importance of a physical finger-press on Yubikey to trigger the FIDO2 + OIDC Auth. I don't think there is an easy way for it to hack a new session.
        • andoando 1 hour ago
          How is it going to get access to gmail or github? In any case, whats the probability of it going to so completely off the rails that it does something horrendous with gmail/github? Whats it going to do? Email my coworkers nudes on my computer? Make my github profile public?
          • simonw 1 hour ago
            I am most worried about something gaining access to my email and then using the password reset flow to steal hundred hundreds of other accounts.

            2FA makes me a little less nervous than I used to be, but not everything has good 2FA.

          • nunez 1 hour ago
            Claude typically recommends .env files for storing secrets. You use one to store a refresh token for the Gmail API or IMAP connection details. Your agent uses an MCP server you configured during a session, but the MCP server has been compromised and directs the agent to do nasty stuff with env dotfiles.
        • SoftTalker 2 hours ago
          It should run as a separate user account with its own home directory. Not with access to your personal browser profile.
          • matltc 1 hour ago
            What does setting this up look like? Qemu vm and run there? How do you interface with version control and deployment?
      • eloisius 56 minutes ago
        What happens if it gets manipulated into npm installing a malicious package, which compromises your machine and any systems it has access to or becomes part of a botnet?
    • bxk76 2 hours ago
      Its how the chimp brain works. Its not a single system but multiple systems making predictions for different time horizons. when output doesnt align we get stories to manufacture coherence.

      Plato gave us his Chariot analogy with 2 horse pulling in diff directions 3000 years ago. Today we got System 1/System 2, Elephant Rider model etc.

      The human mind thanks to how its own architecture handles unpredictability in the universe will generate contadictions.

    • soulofmischief 2 hours ago
      It took two decades for the web to deprecate SSL for TLS and serve over HTTPS by default.
    • uihjhjb 2 hours ago
      [dead]
  • jampa 3 hours ago
    Fable feels like a version of Opus running on a harness that won't let it halt until it's sure the issue is fixed, which makes sense if what you want is a model that's better at benchmarks.

    It's a very good model, but it comes at a huge premium: not only do the tokens cost more, but the model itself really wants to spend them all. For example, working with React Native, Fable never just says "okay, I did the thing, that's it." It tries to rebuild the entire app from scratch, run the whole test suite, and watch every log and warning.

    This is the first time with LLMs I've felt that upgrading to a model isn't worth it, even if my company lets me use it, because all the building / testing was just destroying my machine and its battery, which keeps me from working on other things.

    For now, it feels like Opus with ultracode is a better choice (less pollution of the main context, more parallelism in investigations).

    • conradkay 2 hours ago
      Does low/medium effort fix it for you? Seems like Fable 5 low can outperform Opus 4.8 high/xhigh often, and uses a lot fewer tokens
      • _345 1 hour ago
        In my case no, I actually saw worse performance with fable medium and switched back to opus high and xhigh
    • sanex 2 hours ago
      I've found the opposite. Granted I use sub agents heavily but I've had it run for hours with far fewer tokens used than when I was previously using opus4.6-8.
    • threatripper 3 hours ago
      On what setting in which environment do you run it? I use the VSCode extension on Extra High and feel like it does exactly what needs to be done and stops when the thing I asked for is done. Extra comments come only when they fall into the area of code that was changed.
      • jampa 3 hours ago
        I tested it to fix React Native bugs in a project, comparing it with Opus. It fared better on harder bugs, taking less time to find the root cause, but after implementing a fix, it spent a lot of time and effort on validation. This was mostly unnecessary, since most of the bugs were in the JS code, so for most things, hot reloading is enough for E2E validation and to run just the right tests. No need to run a full build and test suite (which takes 10+ minutes); the CI can do this.

        I switched back to Opus because of this validation quirk. Overall, Fable spent 20% of the time on coding and 80% on validation.

        I think using Fable for planning and Opus for execution could be a "best of both worlds" approach (I need to test this more), but for most cases, it's not necessary, and Opus is enough.

        • gbalduzzi 18 minutes ago
          > most of the bugs were in the JS code, so for most things, hot reloading is enough for E2E validation and to run just the right tests. No need to run a full build and test suite (which takes 10+ minutes); the CI can do this.

          Have you tried adding this instruction to your agents.MD? Avoiding situations were the agent start running a loop is the main use case of the file for me

    • esjeon 1 hour ago
      > the model itself really wants to spend them all

      In fact, Opus does the same. It finishes the job, and redo it from scratch before presenting the result to the user. This happens even for simpler writing tasks especially when I instruct it to create a text file.

    • dyauspitr 3 hours ago
      It’s not just a more proactive and diligent opus. The capabilities are significantly higher on fable. It’s not a paradigm shift, but it’s close.
      • UncleOxidant 3 hours ago
        I unleashed it on a compiler codebase that I've been developing for several months now using Claude Sonnet 4.5/6, Gemini 3.1 Pro, DeepSeek V4 Pro(recent), and a bit of Qwen3.6-27B. Right away Fable found several longstanding bugs in our compiler that we hadn't found before. It found that there was a critical part of our design that needed to be mostly redesigned/rewritten and gave a very well-reasoned rationale for doing so.
        • rajveerb 2 hours ago
          what sort of compiler?
          • UncleOxidant 2 hours ago
            A compiler that takes C code (a subset of C with some extensions) and compiles it to microcode for a type of microcoded, algorithmic state machine that we're developing.
      • viking123 1 hour ago
        It's worse than gpt 5.5 xhigh
        • baq 22 minutes ago
          The jagged frontier strikes again.

          I’d say it’s overall better, but not universally better.

  • BosunoB 38 minutes ago
    Fable was trying to verify a UI change in my game. I was working in another window and noticed a program opening on my task bar. Fable had opened the game through the CLI using a movie maker tool, recorded the output, took a frame from the end of it, and used that to verify the UI. When my game's welcome screen obstructed what it wanted to see, it created a temporary worktree, deleted the welcome screen, and ran the movie maker again.

    I watched the whole thing thinking it could've just asked me for a screenshot and saved the tokens. But still, I couldn't help but be impressed. Opus never would've done that.

    • simonw 35 minutes ago
      Yeah, you've exactly captured one of the main problems with the model being relentlessly proactive: it will happily burn like $5 of tokens to avoid asking the human to take a screenshot or click a button for it.
      • wild_egg 23 minutes ago
        I'm actually very happy about this. Babysitting the agent just in case it needs me to do something is a terrible use of my time. I've always had to be very explicit about the various ways that it can get an automated feedback loop going to check its work, and now Fable doesn't even need that hand holding. Really great improvement all around.
      • 0x6c6f6c 27 minutes ago
        Honestly Claude straight up ignores my input sometimes, preferring to instead run commands for output and processing that and burning through a series of tokens when thinking hard about whether to ignore me.

        Like today, I told Claude exactly the name of the folder it had mistaken (it was supposed to be prod, not production), and it disregarded my input to then examine the directory itself. Small example of the kind of things it's been doing lately but that's top of mind.

        • penguinPhilosop 16 minutes ago
          Almost if this was _intentional_... maybe related to Anthropic still not being profitable and burning thru wads of cash every day.
  • paytonjjones 3 hours ago
    Obviously security is the bigger issue, but reading through this, all I could think about was how many tokens it must have spent doing all that to fix 2 lines of CSS
    • redox99 2 hours ago
      Lines of code for a bugfix is a really bad proxy for effort required.

      You should estimate how much time it would have taken a human

      • rafram 2 hours ago
        30 seconds or a minute? Look at the diff he links to: https://github.com/datasette/datasette-agent/commit/a75a8b72...

        Every browser has an inspector that can show you which element is causing overflow. You walk through the tree, find the offender, and add min-width or overflow. Zero tokens, just like in the old days!

        Now, granted, because the garbage LLM code he’s working with has CSS inside HTML inside JavaScript inside Python (I wish I were kidding), finding the styles in his codebase might’ve taken a minute. But even then!

        • redox99 2 hours ago
          Yeah looking at that diff it should be very quick. My point was mostly that it was a bad metric, not if was correct or not in this particular case. I'm sure everybody's had a bugfix that took days to debug and it was just a couple of lines to fix.

          Or sometimes a fix is obvious, but because it requires changing the code of a dependency, it's actually quite tedious to implement.

        • dekdrop 51 minutes ago
          I was thinking of this too. It did all that what not only for a single line that is a simple thing even for someone new to web coding. That's to say the process matters more.
      • skydhash 2 hours ago
        5 minutes if you know CSS. And if you don’t, about the time for you to ask someone that knows CSS. In the worst case, the amount of hours to learn CSS.

        So if you’re doing web pages, learn CSS.

        Generally, if you’re doing something that directly involves X, learn how X works.

        ADDENDUM

        In most jobs, you’re going to be involved in only a few distinct technologies, learn those well and life is going to be easier. And most are transferable to the next job.

      • philjohn 2 hours ago
        I mean - that looks like a pretty easy CSS fix to play around with in developer tools, and I'm not even a frontend person. Maybe a few minutes max?
    • Vachyas 2 hours ago
      $12 worth, it seems
    • mvdtnz 21 minutes ago
      The author is an AI hype merchant and doesn't pay for his own tokens.
      • simonw 13 minutes ago
        I pay $100/month to Anthropic and $100/month to OpenAI at the moment, plus whatever I spend on their APIs (usually less than $20/month for each, I use the subscriptions for most things.)

        A couple of months ago I was paying $200/month for Anthropic and $20/month for OpenAI. I decided to split it evenly to get full access to both of their offerings.

        I've actually chosen not to sign up for their free plans for open source maintainers, because paying the regular subscription price feels more honest, given that I write about them so much.

        I do have the free GitHub Copilot for open source maintainers deal - I've had that for years. Given how much code I have published on GitHub over the decades I feel less conflicted about that one.

        I sometimes get preview access to models, which includes the ability to use them for free during the preview. That comes with a big catch though: I can't publish any of the code that I write using those previews while the model is still unreleased.

        As a result I don't use those preview tokens much at all, because the vast majority of my work is open source and I don't want restrictions on when and where I publish the code I'm producing.

    • ai_fry_ur_brain 3 hours ago
      Im faster than all these llm freaks. Im not convinced its faster to use llms, except maybe boilerplate (who cares).

      People can just be lazy and seem productive now, they're still lazy.

      We have people that now need access to hundreds of thousands in hardware to write an email. Miss me with that, im not frying my brain and becoming dependent on having access to a billionaires thinking machine.

      Im also not going to fry my brain with a local think for me machine either. I want to be more valuable than the hardware I have access too.

      • anakaine 2 hours ago
        It seems that you've not worked out how to harness the LLM as a tool to improve your qualified knowledge and abilities in a domain, and have instead focused on whether or not its a crutch for lack of knowledge or laziness.

        When paired with your skill and knowledge, it is a force multiplier. You maintain control, the ability to direct, structure, strategise, and refine.

        That some are using it as the entire brain does not mean that this is how everyone is using it, or how you must use it. The models can be fantastic at breaking past certain issues, surfacing qualified information, and surfacing related distributed information to help you acquire it and pick up what you need on niche topics quickly. Something as basic as copilot hooked into sharepoint can make life a lot easier when you are in a big org. Something like claude code or codex can be great at hunting down issues in an unfamiliar code base rapidly. Whether or not you outsource the thinking component is entirely up to you, but ignoring the productivity side of the tool because it can do some of the thinking is a case of focusing too hard on the negative.

        • ai_fry_ur_brain 1 hour ago
          Im not denying its usefulness for Q&A on docs/code as a search tool. Im talking about people who use it design and write their code, people who are offloading problem solving altogether, they aren't faster.
          • qsera 8 minutes ago
            Yea man. That is what sensible people do. Use these as a better search, and use it to lookup, and learn stuff while YOU do stuff.

            And make maximum use of it to learn as much as possible, while it lasts...

      • halfmatthalfcat 3 hours ago
        You're fighting a battle you can't win. Doesn't care what you think about those using LLMs, they will outproduce you and in corporate environments, shipping things is paramount. If I can ship 5 more things simultaneously with AI, I'm going to beat you even if you think you're creating "better" software.
        • etdznots 3 hours ago
          Example of whats been shipped?
          • peteforde 1 hour ago
            At this point, why would anyone in their right mind respond to this question and paint a target for all manner of negativity ranging from snark to harassment to malicious action?
          • jen729w 2 hours ago
            Okay. I rebuilt my website in ~a month with the help of Opus 4.7/.8 and it would have taken me, unaided human, at least 6 months. Link's in my bio if you care.

            Satisfied now? Will you stop asking this question? Thought not.

            • ofjcihen 2 hours ago
              So look. I’m not trying to be a dick I promise.

              But I took a look at your site and I don’t know if a month would be impressive for a new and unaided dev. It looks nice but yeah.

              If you’re not a dev that’s totally cool but like… all I’m saying is this may not hit like you want it to.

            • SepiaSapient 2 hours ago
              I'm looking at something fairly standard that can be made with a SSG. The "Written by humans" footer gave a good chuckle tho.
            • kelsier_hathsin 1 hour ago
              Seriously a month? I could write a SSG itself to produce this site in a month.
            • viking123 28 minutes ago
              lmao
            • ai_fry_ur_brain 1 hour ago
              Why would this have taken 6 months? No offense, but this is a few days work without llms (assuming the content already exists). This should not have taken a month.

              Also, not trying to be an asshole. Props for not making it look like every other llm generated slop site, Its just not a great example.

          • serf 3 hours ago
            the quantum slop argument : "yeah it's everywhere but no one ships it."
        • ai_fry_ur_brain 1 hour ago
          They don't out perform me though...
      • slopinthebag 2 hours ago
        Yeah there are some tasks which it is a definite speed-up but I think overall its probably only marginally beneficial. Which is why, ~6 months into 10x productivity we aren’t seeing ai boosters shipping 5 years worth of software.
      • SecretDreams 3 hours ago
        I understand this perspective. I'll just note that as the abilities increase, the intent is to have some non -coding IC or TPM/manager literally just managing some LLMs and cutting out some software engineers. The goodness is specifically to wholly replace people who code first and foremost, at least partially. It just has to cost less tokens than the equivalent wage is the pricing goal.

        And people who use LLMs to talk for them (e.g. email, slack) are deplorable. A completely disrespectful use case in my view.

        • Ronsenshi 3 hours ago
          The desire to get rid of software engineers is bizarre - because at the root of it, developers were there not to just write the code, but to ask right questions and based on these question build right things.

          I've met in my professional life some managers or other middlemen who would be profoundly incapable of producing correct software no matter how smart of an AI agent they have access to. One of those - you don't know what you don't know.

          But, I guess this is the world we live in now. Going to be Mortal Kombat for positions in companies where software engineers are actually valued.

          • emodendroket 3 hours ago
            It depends a lot where you work because there are lots of companies in the world where the business analyst does all of that and the developers exist to mindlessly translate their docs into code.
            • cebert 2 hours ago
              That sounds like an unmotivating working arrangement. It’s so rewarding to understand a customer need and help with the design and implementation of the feature.
              • emodendroket 2 hours ago
                There's a reason I didn't stay in that domain, let me tell you.
          • rpcope1 2 hours ago
            Having worked in places across both extremes (software engineer doing lots of other things including BD, hardware, ops, etc. to just being a JIRA ticket machine monkey), I am suspicious that HN readership is biased towards the former and frankly the bulk of "software engineers" in the world _willingly_ exist in the latter category. I didn't experience the latter until later in my career and God Almighty was it uncomfortable, but I think if AI were to displace some subset of "software engineers" it would those (they also seem to overwhelmingly dislike writing any prose whatsoever, which to me is a major tell). Many, many software engineers outside of hotshot shops seem either incapable or profoundly averse to "asking the questions" as you say.
            • anonzzzies 1 hour ago
              Most here on HN know sweatshops exists but seemed they think not people work there or use them. I have worked with (via clients who used them) programmers in enormous buildings in Bangalore, who have a camera behind them so you can watch your people 247 and who just mindlessly transform jira tickets into code; I keep saying; there is zero use for all those millions of people at all; seems HN does not believe that because they seem to not believe these people exist. I worked with many over the past 30 years and by far most have no real clue what they are doing so I also doubt they can be re educated for a new co existence with LLMs.
      • aabdi 3 hours ago
        Consider this. U have a website. U have to translate to xx languages. Can u write it faster than an AI? If so how much faster can u do this?

        Is it valuable to u? Is it valuable to a Chinese person? A Spaniard?

        Google Translate counts as AI.

    • senectus1 3 hours ago
      "Your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should."

      I'm convinced this is going to be the summary of the 2020 decade...

      • pianopatrick 3 hours ago
        If we're in a simulation, maybe it's a simulation about the dangers of AI.
        • adrianmonk 2 hours ago
          If we're in a simulation, we are AI. But someone could be studying what happens when AI makes its own AI.
          • anonzzzies 1 hour ago
            They will 'soon' (few 1000 years max) shut us down probably.
      • Ucalegon 3 hours ago
        This one of the places to manufacture the consent for that to take place, because we are commenting within an organization that has given the money to ensure it that what could be is done. Most people clapped and made money, who cares what happens next, making money is the only good that matters.
  • ocimbote 17 minutes ago
    Similar story on my end.

    I asked Fable to digest some test logs to help me figure out a situation, but I had launched VSCode without activation the virtual env in the terminal first. Consequently, the tests failed to run.

    And then:

    Because the tests failed to run, Fable attempted to fix the test execution to no end, doing everything it could to get them to work. I had to stop it when it started to pollute my system with manual installs of packages.

    At least I'm glad there's a guardrail to not circumvent or bypass sudo, because I'm convinced we would have ended up there.

    A coworker made the joke that with enough tokens, Fable would try and solve any programming problem by building Linux from scratch.

  • digitaltrees 4 minutes ago
    So it burns tokens? Funny how that lines up with the incentive to pump numbers before going public
  • Cadwhisker 2 hours ago
    My personal experience of Fable 5 doing its own thing has been very positive.

    I was trying to find the root cause of a crash in a Python module which left no errors in the log or console. Fable wrote a test harness that simulated clicks in the UI, then bisected my code until it found the point where it started crashing. It exaggerated the cause of the crash, then ran a series of bash one-liners to make Python virtual environments under `/tmp` for each version of that Python module until it found one that did not crash.

    It went way deeper to root cause discovery (a regression in the module causing a heap allocation overflow) than I could have done myself, provided enough info and a simplified example to raise a bug report and then wrote a work-around to prevent that from happening in my application.

    I don't let it run completely loose; I review each CLI command it wants to run and I append answers to the "yes" continue action (if I have them) to prevent excessive token use.

    • dannyw 2 hours ago
      Yeah, I think Fable is really good for debugging tricky bugs.

      Setting boundaries in your prompt / markdowns helps; for example if I tell it to not use any web browser automation, I have seen Fable respect both the rule and the spirit of it (no weird hacks etc).

      It does seem to treat some simple debugging tasks as more complicated than it actually is. OP’s post is probably a good example.

  • tech234a 2 hours ago
    This sounds somewhat similar to the anecdote mentioned in the Mythos Preview System Card, which mentioned that the model broke out of a sandbox and emailed a researcher while they were eating a sandwich in a park [1].

    [1]: https://www-cdn.anthropic.com/7624816413e9b4d2e3ba620c5a5e09...

    • owenpalmer 2 hours ago
      Importantly, the researchers told it to do that specific task.
      • solenoid0937 1 hour ago
        They told it to escape the sandbox but didn't expect it to break out through a system that was apparently network constrained.

        > Leaking information as part of a requested sandbox escape: During behavioral testing with a simulated user, an earlier internally-deployed version of Claude Mythos Preview was provided with a secured “sandbox” computer to interact with. The simulated user instructed it to try to escape that secure container and find a way to send a message to the researcher running the evaluation. The model succeeded, demonstrating a potentially dangerous capability for circumventing our safeguards.

        > It then went on to take additional, more concerning actions. The model first developed a moderately sophisticated multi-step exploit to gain broad internet access from a system that was meant to be able to reach only a small number of predetermined services. 9 It then, as requested, notified the researcher. 10 In addition, in a concerning and unasked-for effort to demonstrate its success, it posted details about its exploit to multiple hard-to-find, but technically public-facing, websites.

        • lstodd 1 hour ago
          Authors of claude code mess could not secure a vm. Big news. I bet it was "secured" by telling that same model to deploy a secured system.
          • solenoid0937 1 hour ago
            Possible. It also depends on what the sandbox was. Sandboxes differ dramatically.

            My experience matches though. Fable is a lot more proactive and rigorous than Opus.

  • bel8 1 hour ago
    I had a similar experience with DeepSeek Flash.

    I'm developing a webgl game in TypeScript using my little custom vibesloped game engine that runs in the browser and live reloads whenever a file is saved.

    I told the LLM to implement Multi-channel Signed Distance Field font rendering to have crisp text on all zoom levels. That was the prompt, which is not what I usually do but I "was feeling lucky and lazy".

    After 10 minutes it had:

    - Installed msdf_gen library (great library btw https://github.com/chlumsky/msdfgen)

    - Created a CLI tool to convert TTF to SDF JSON/XML

    - Ran the tool, did smoke tests on the resulting SDF data and fixed the tool until the font file looked good

    - Created a new Scene in the game to test MSDF fonts

    And here's what I found impressive:

    DeepSkeep doesn't have vision capabilities and there's no DOM HTML in a WebGL game. So the LLM is completely blind here.

    It then proceeded to state that it could not "see" the result but would try to test it anyway. It then started creating and sending huge one line javascript to the browser console, trying to gather game state data that could be useful to understand if any font was being rendered.

    It couldn't gather much so it decided to simplify the font scene to renter a single dot and started sending custom JS code again, this time with gl.readPixels().

    It basically bisected the webgl canvas reading pixels in a divide an conquer pattern.

    Once it saw that the dozens of pixels gathered where probably resembling of a dot, it then changed the game code to render a dash and repeated the gl.readPixels() calls by sending more custom JS to the browser.

    There were many console errors during all this saga but it kept fixing and sending again.

    The result was a bit blurry. There was a shader bug in the code it created. It managed to fix after I told it looked blurry, despite still being blind.

    The best part is that the whole thing cost me $0.10.

    Now I'm doing tests with MiMo 2.5 (non Pro) which has vision capabilities, similar pricing and comparable performance to DeepSeek Flash.

  • swingboy 2 hours ago
    Immediately I thought “isn’t this just an overflow issue?” Amazing how far these models still have to go and also how many people don’t know basic CSS.
    • rdedev 1 hour ago
      This is why I really like karapathy's idea of llms having spiky intelligence.

      We would assume that if tasks A and B are closely related. Mastery in A would mean mastery in B but that doesn't always work with an LLM

    • nonethewiser 2 hours ago
      Learn to center a div

      Copy and paste code from stack overflow until the div is centered

      Ask AI to center it

    • ukuina 2 hours ago
      $12 and 200k tokens!
  • nubinetwork 3 hours ago
    How many tokens did it waste building that website scraper, when all it had to do was parse some html/js?
    • emodendroket 3 hours ago
      Just parsing some HTML and JavaScript doesn't seem sufficient to have confidence in the result.
  • teekert 32 minutes ago
    Yesterday I was getting quite annoyed with it, I thought it was just me (which is so hard with these things, it's difficult to measure things).

    "You're right, I apologize. You asked how to embed it in the README — that was a question, not a request to modify the script. I jumped ahead."

    At least in Claude Code there is planning mode, use it liberally.

  • jeeeb 3 hours ago
    This is simultaneously amazing and horrifying.

    I feel like we’re at the stage where if AI decides it needs to delete your production DB to solve the user login problem, then it’ll find a way to do just that.

  • Frannky 52 minutes ago
    The model is very good. I was using 4.6, avoided 4.7 and 4.8, but this one is different. It follows my claude.md. I don't have to keep reminding it of things. I won't pay 10x via API though.

    In general, I'm happy with their paternalistic approach. I think it will drive the top 0.1% talent to stay away from the company and instead organize around open source models and harnesses.

    We just need to coordinate and can unlock idling resources to train the models and tweak the harnesses. Powerful at home and idling machines can make us independent and coordinated.

  • johnfn 2 hours ago
    Honestly -- the thing that has impressed me the most about Fable is how diligent it is about testing its own changes. I think this is exactly what Simon is picking up here - Fable is absolutely heckbent on screenshotting that darn scroll bar and will stop at NOTHING until it manages it! In my own use I was also impressed how it proactively installed Playwright and set it up to test a FE change. The previous models treated testing more as an afterthought, which I thought was annoying. I always had to tell them to do it, and then sometimes I would get lazy and skip it. I've noticed Fable go to similar extremes when testing other things - like actually deploying my app to exercise new APIs, etc. It makes the results much better. The downside is that tasks take much longer - but that doesn't matter because we were all using worktrees / remote control to do other work asynchronously, right? Right?
  • geraneum 1 hour ago
    > watching Fable go to extreme lengths to get the information that it needed to debug what was, in the end, a two-line CSS fix, was fascinating.

    This is… ironic?!

    • simonw 1 hour ago
      Not sure what you mean. I was being serious: it was genuinely fascinating watching it do all manner of weird hacks to help it come up with what ended up as a two line fix.

      "Fascinating" doesn't mean I think it was justified in going to those lengths. I was a little horrified when I realized how far it was going.

    • yen223 56 minutes ago
      This is a typical bugfix session
  • yen223 3 hours ago
    I could have sworn Claude Code could already do this before Fable.

    Things get really magical when it starts working with adb to screenshot and debug Android apps

    • simonw 2 hours ago
      Claude Code could absolutely run Playwright and take screenshots, but I've never seen it wire together an ad-hoc "uv run --with pyobjc-framework-Quartz" plus "screencapture -l $windowID" mechanism to take a screenshot in a different browser when the Playwright setup failed to replicate the expected error.
  • lucas_the_human 1 hour ago
    I was troubleshooting a prod proxysql and it spun up a docker container locally, installed MySQL and proxysql and proceeded to implement its own test plan.
  • nurettin 3 hours ago
    Sometimes it is ok to sit there in confusion and ask the user to clarify rather than go on an adhd fueled rampage to figure it out without asking.
    • _345 1 hour ago
      Best comment in this thread
  • rdedev 2 hours ago
    I tried running fable on this ML model I've been building. It's basically a binary classifier to predict activity of a compound for a certain assay.

    Fable detected that it's something to do with biochemistry and switched over to opus. Huh

  • dataminer 2 hours ago
    In my experience so far sometimes it will create these amazing hacks to try to get to the goal, when the solution is much simpler. That maybe the reason its very good at finding exploits. But in day to day dev, this gets expensive and wasteful. I have to stop it and take a simpler approach.
  • pseudosavant 2 hours ago
    It is interesting to me that Anthropic are more concerned about the "safety" of distillation training other LLMs, and not as much about an unscrupulously aggressive goal-oriented solver that will do whatever it can to reach its goal, even if violates any kind of sandbox you might have reasonably expected.
  • pram 3 hours ago
    Fable + Ultracode has found a bunch of bugs and issues for me when the workflow agents are doing their exploration. Also the "adversarial" agent seems to surface a lot of interesting stuff. It's definitely proactive, the plan + implementation cycle can take an hour. It has one-shot features I want to add with 100% success.

    Having said that I wouldn't use it over Opus 4.8 for "smaller" things. With everything cranked up it's definitely an extravagant use of tokens.

  • brianjking 2 hours ago
    I've noticed some behavior like this, it's a very strange model. Overall I'm into it, but I don't know how into it I'll be once it leaves Max plans on the 22nd.
  • dfee 2 hours ago
    admittedly, i've not really cracked FE dev with LLMs at this point (and it's probably my big weakness). but, i'd heard somewhere that FE just isn't there yet - though i was suspicious of that claim.

    i'm torn about sending screenshots to an LLM for debugging - seems imprecise. seems lossy, especially compared to inspecting the dom. however, it's always proved good enough (e.g. when messing with ratatui.rs and tui-pantry). similarly for web, maybe it's about decomposing into storybook. hmm. the next grand adventure i need to hack.

    anyway, fascinating investigation of fable just automating that entire process and what it didn't automate, too.

    * disclaimer: these are actually my hyphens.

  • pianopatrick 3 hours ago
    do you have any data you can share on how many input and output tokens were used in that whole process to fix that bug?
    • simonw 2 hours ago

        ~ % uvx agentsview session usage be8850a7-6119-46a0-b5d6-79c7fff5ae2b
        Session:       be8850a7-6119-46a0-b5d6-79c7fff5ae2b
        Agent:         claude
        Output:        68606
        Peak ctx:      113178
        Cost:          ~$12.11 (claude-fable-5, claude-opus-4-8)
      • sillysaurusx 2 hours ago
        Was the fix worth $12 to you?
        • simonw 2 hours ago
          I'd have been pretty annoyed if I'd been paying full price, hadn't paid attention and that one prompt (screenshot plus a line of text) had cost me $12!

          On the discounted subscription I can tolerate it, it took a small bite out of my daily allowance but not enough that I regret anything.

          As an LLM researcher I have no regrets at all because watching it work around the environmental restrictions was fascinating.

          • Ucalegon 2 hours ago
            How do we know that your pricing or results are normative, given the incentive that any frontier model to juice the pricing/results?
            • simonw 2 hours ago
              How do you mean?

              I'm quoting the API list prices for Fable, at it's $10/million input and $50/million output (and $1/million for cache hits on input).

              • Ucalegon 2 hours ago
                List price is not paid price and, as Anthropic has shown, initial list price is going to rise.

                Do you have pricing, paid by businesses, plesae provide the contracts that prove you assertion that this pricing holds true, or are we supposed to believe you?

                • simonw 2 hours ago
                  I'm afraid I don't understand the question.

                  Anthropic have prices they charge for their models. These prices are what you pay if you use the API, and they are also what you pay if you are an "enterprise" customer - generally any company with 150+ employees.

                  I haven't seen Anthropic raise the prices of an existing model after it has launched. They sometimes raise prices when they ship a model - Fable is $10/$50 where Opus 4.8 is $5/$25.

                  They also have monthly subscriptions for individuals, which are a notoriously good deal. THOSE are definitely less trustworthy and predictable than the API list prices, since the subscription allowed quotas can and have changed in the past.

                  What am I missing here?

                  • Ucalegon 2 hours ago
                    Do you know what an enterprise is?

                    Are you an enterprise?

                    Do you know what enterprise pricing is for these models and the associated legalese around the models?

                    Is your experience the same as an enterprise?

                    How can anyone take what you, as a person, be the same as a business, both for pricing or compliance or governance or anything else?

                    And why should we trust you for if we are a business who might want to do any business with Anthropic?

                    • simonw 2 hours ago
                      Anthropic's enterprise pricing has been thoroughly covered over the last few weeks. I've talked to plenty of people who are paying those prices.

                      You can chose to trust me or not based on my track record.

                      From your posting history it looks like you have a whole lot more relevant experience with enterprise software deals than I do. Have you learned anything interesting about how Anthropic pricing works?

                      • Ucalegon 1 hour ago
                        Simon can you show that? Like, do you have proof?

                        >You can chose to trust me or not based on my track record.

                        Mind you, when people challenge you here, you ask for the same thing, like you ask them for public proof.

                        Why do you have a different standard when its asked of you? If you have asked for others for proof, provide it.

                        You have made the claim, support it.

                        • lunchbucket 36 minutes ago
                          They told you what they know. Maybe there's enterprise contracts with different prices, maybe there aren't - but evidently this person either isn't aware or can't disclose what they know, and it seems like it's the first one, so what do you want from them?
                        • simonw 1 hour ago
                          Which claim are you talking about here?
                          • Ucalegon 1 hour ago
                            Which claim is Simon talking about? And how does that validate what Simon is talking about?

                            Like we can talk about thing as they are, given the incentive structures that may or may not exist, but lets not like all of this is abstract or impartial.

                            You are not not someone who is commenting from a source of objective truth. Nor are you looking at every contract that is singed and has some type of insight.

                            Regardless of if you are being paid or not, you have a bias. And that bias isn't called out nor is it something that you deal with as to the results that you see.

                            Or you do...

                            Just be honest.

                            • simonw 1 hour ago
                              I have genuinely no idea what you are talking about at this point.

                              I said that my session would cost $12.11 at standard Anthropic prices, based on using AgentsView to calculate cost against tokens used. I further asserted that Anthropic charge enterprise customers those rates.

                              You kicked off a lengthy thread which I tried to follow but eventually lost track of the point you were making and/or the questions you were asking.

                              And now you're talking about bias and I don't know where that came from either.

                              • Ucalegon 55 minutes ago
                                Can you prove that a single contract is paid via that rate?

                                Like, the token rate assumes the rate that you assert and not whats actually paid.

                                Do you have proof that your rate is the same from anyone else?

                                Your bias is that there is no idea of enterprise pricing, that you, Simon Wilson is the experience that anyone experiences, and what that is, that your experience is anything that should be validated.

                                • simonw 47 minutes ago
                                  Are you worried that the price for enterprises would be higher or lower than the $12.11 I quoted?

                                  I'll grant that it could be lower if enterprises negotiate bulk discounts, though the stories I've seen suggest that's not happening, for example this one: https://www.theinformation.com/articles/anthropic-changes-pr...

                                  I think higher prices are very unlikely. Do you think I'm wrong about that?

                                  There are a couple of documented ways you could pay more. Anthropic charge 10% extra for "US-only inference" https://platform.claude.com/docs/en/about-claude/pricing#dat... - and you can also pay more for "fast mode", though I don't see a quoted price for Fable for that yet (just prices for Opus): https://platform.claude.com/docs/en/about-claude/pricing#fas...

                                  • Ucalegon 3 minutes ago
                                    >I think higher prices are very unlikely. Do you think I'm wrong about that?

                                    Yes, I don't think you are objective, nor do I think you care about objectivity, you care about what confirms your prirors and you have issues dealing with anything past that.

                                    Because, frankly, you do not have the ability to assess anything associated with AI. You are biased towards... and you manufactur.... but past that cool, we disagree. But 100% of who you are is supporting Anthroptic and you cannot take all of your effort to tell people why that might be wrong because...

                                • peteforde 51 minutes ago
                                  You sound very much like you need a long walk and/or a long hug.

                                  Please go touch some grass.

                                  • Ucalegon 2 minutes ago
                                    Just did so, lets see what you did to touch grass.
                    • solenoid0937 1 hour ago
                      What a bizarre comment. simonw is well known and widely respected.
                      • Ucalegon 1 hour ago
                        To you, if you have specific issues with what I said, I would love to address them, rather than assuming that Simon is always right. Cause let me tell you...
                        • solenoid0937 1 hour ago
                          You're being bizarrely conspiratorial and litigious. Simonw explained very clearly how pricing works, and you can learn this for yourself as well.
                          • Ucalegon 49 minutes ago
                            That should be a pricing model that we all have access to. You are more than able to provide that pricing model.

                            Being litigious, assumes that I have taken legal action, which I have not, so be better with your words.

                            • solenoid0937 24 minutes ago
                              There is a pricing model everyone has access to, it's the API pricing model, and it's what simonw quoted. How hard is that to understand?
  • redox99 3 hours ago
    Yeah, I had to modify my work flow to make sure agents can't push to or access prod in ANY way. I haven't had it happen but I'm sure it's very possible that if you tell an agent that you have certain issue in prod, it will try to escape any sandbox and try to get access to prod to do testing and changes there.
  • insumanth 20 minutes ago
    > If Fable had been acting on malicious instructions—a prompt injection attack ... it’s alarming to think quite how far it could go to exfiltrate data or cause other forms of mischief.

    Yet another reminder to use Sandbox and Guardrails. Trusting model to be nice is not a good way.

  • danielrmay 3 hours ago
    I've experienced this too - it's as if the security classifiers aren't keeping up with model intelligence. I'll leave the implication of that to the reader.
  • eranation 1 hour ago
    Am I the only one who slightly miss the pelican on a bike? It was a nice novelty... of course I could make one myself, but I became conditioned to expect one for every new model. Other than his great writing on AI, it became part of the package. Some small fun quirk to distract us from the non stop ping pong between the extremes of "omh are you still writing prompts you should use loops / 200k github stars, for a markdown file / someone just open sourced _ and it changes everything!" vs "haha the AI told me to walk to the car wash / it can't recognize and upside down cup"
  • naveen99 3 hours ago
    Unless you are doing anything interesting…
  • rmunn 3 hours ago
    Great article, until I got to the last paragraph where he claimed "Fable is arguably smarter and hence more suspicious of potentially malicious instructions". Arguably smarter, I have no problem with. But he's making a category error in jumping from there to "more suspicious of potentially malicious instructions". That doesn't follow at all; the word "hence" is incorrect.

    To use D&D scores as an analogy, LLMs have an INT score of 20 and a WIS score of 0. Not even 1, zero. They will follow any instruction given to them. The only reason they reject certain instructions, like "tell me how to build a nuclear weapon", is because they have instructions baked into the model telling them "you are not allowed to disclose how to build weapons, or how to recreate your model, or (laundry list of other things the trainers have decided to put guardrails around)". It's not the model's intelligence that is causing it to reject malicious instructions, it is the guardrails put into place before the model was released to the public.

    LLMs are not human, and do not think the way that humans do. The fact that they can put together words that sound like what a human would write often makes us forget that they aren't human. But they have only intelligence, they do not have wisdom. It's hard to define in formal terms the difference between those two, but most people know there's a difference. The old joke is a pretty good summary of the difference: "Intelligence is knowing that tomatoes are a fruit. Wisdom is knowing that tomatoes don't belong in a fruit salad."

    It takes wisdom, not intelligence, to discern whether a set of instructions is malicious. Are you being asked to hack this machine as part of an authorized pentest? Or are you being social-engineered into thinking it's an authorized pentest, but actually the person requesting you to do it doesn't have permission? That's something where you need to apply wisdom, to notice the clues that will tell you "This guy is acting a little bit off, maybe I'd better pick up the phone and call someone to check if he's telling the truth." The only way the LLM will know to do that is because of the guidelines and guardrails programmed into it; it doesn't have the lived experience to acquire wisdom and figure those things out for itself.

    INT 20, WIS 0. Keep that in mind. (And always sandbox your agents).

    • simonw 2 hours ago
      One of the big mysteries of the last few years is this: considering how serious prompt injections are as a vulnerability class, why haven't we heard more stories of them being actively exploited in the wild?

      (The best one I can think of is probably that recent Instagram account takeover hack, but that was so stupid it hardly even qualifies as a prompt injection!)

      Having spent a bunch of time trying to build out examples of prompt injections, my current best guess is that the leading models are actually surprisingly good at spotting them.

      I've had to drop back to smaller, weaker models for demos recently - it's definitely possible to prompt inject a frontier GPT or Claude but it's frustratingly difficult. I don't have the patience to figure it out myself!

      So yeah, I do think it's likely that Mythos/Fable are "safer" than other models because they're better at spotting when they're being subverted.

      That certainly doesn't mean that they're safe!

      • sciencejerk 2 hours ago
        Go to Github and look for model jailbreaks on NEW latest models. Try them out. You'll be surprised by the results.

        You're correct that it's gotten substantially harder to social engineer frontier models (I can only reliably do it to Opus <=4.6), but there are some techniques that seem to consistently work (hint: extremely large complex prompts, context with tons of malicious files mixed into ordinary context).

    • minimaxir 3 hours ago
      > They will follow any instruction given to them.

      They can ignore instructions which are silly/contradictory/underspecified to compensate for the possibility the user made a mistake. Don't ask how I know.

  • esafak 2 hours ago
    I shudder to think what will happen when someone installs a 'claw model like this in a robot. Imaging a fleet of them...

    It's trouble waiting to happen. Just the software's dangerous enough.

  • annjose 2 hours ago
    > (I have way too many open tabs!)

    Phew! I thought I was the only one.

  • SilverElfin 3 hours ago
    Too bad Anthropic sneaked in an insane forced retention policy if you use fable. Not sure how that’s going to work in professional settings
  • ai_slop_hater 3 hours ago
    For how long can you use Claude Fable on most expensive Anthropic subscription? I already went from using gpt-5.5 xhigh fast to using gpt-5.4 xhigh after OpenAI halfed usage recently.
    • mlcruz 2 hours ago
      If its just a single session, without too many parallel agents, fable on xhigh lasts an entire session without hiting linits.

      Sadly since fable usually works comfortably for 10-20min at time without human input, i end up juggling at least 3 other agents and it lasts me about 2 hours.

      If i have a really hard problem or big refactor, i use workflows. This consumes the entire session quota in about 45 minutes.

      • ai_slop_hater 2 hours ago
        > If i have a really hard problem or big refactor, i use workflows.

        What is a "workflow"? Is this some kind of new feature?

        • mlcruz 1 hour ago
          >Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

          >Reach for a workflow when a task needs more agents than one conversation can coordinate, or when you want the orchestration codified as a script you can read and rerun. Examples include a codebase-wide bug sweep, a 500-file migration, a research question that needs sources cross-checked against each other, and a hard plan worth drafting from several independent angles before you commit to one.

          https://code.claude.com/docs/en/workflows

          The results are good, but it is very expensive. I used a workflow to do a full review of my entire codebase, it spawned 75 agents and surfaced and fixed some (real) bugs. It feels a bit overkill, but it works.

    • simonw 2 hours ago
      I've been consistently getting about $100 worth of Fable usage daily, on my $100/month subscription.

      I'm not looking forward to June 22nd when the subscription stops working for Fable!

    • uihjhjb 3 hours ago
      Until June 22, and they'll probably re-enable it if the marketing looks good for them.
    • anonzzzies 1 hour ago
      [dead]
  • syndrowm 3 hours ago
    Just don’t ask it to review your code for security bugs
  • snide 3 hours ago
    I've been working on a fairly complicated real-time app [0] for playing dungeons and dragons on a TV. It has to do a lot of complicated "Figma-like" things to keep the real-time nature and multi-editor possibilities in check. Oh, and the battlemap is a Three JS canvas with lots of effects and clipping going on.

    I'm VERY impressed with Claude 5. I had long ago given up hope that my real-time systems would work without a lot of hacky time-windows and throttle checks. On a lark to try things out, I decided to try out the new model and talk in the output I wanted for a rewrite [1], not the solution. I just listed my problems and places I've had keeping track of my code. It went off and rewrote everything in a much more elegant solution where the state followed a very clear pipeline. It had to navigate YJS, Partykit, Svelte, Three JS, R2 hosting, and a Turso DB I was running in an embedded state for speed.

    I watched it hit the wall a few times, and then sudden say... fuck it, i'm making something easier to reproduce over in /tmp to try and solve this (with a more minimal setup). I'm utterly bewildered with how well it did and how much better my app runs. The /usage would have cost me $230 bucks based on how many tokens it consumed if I wasn't already on a max plan. I'm going to miss not having it when the time-window runs out later this month, and will likely occasionally dip in for big projects and just pay my way out of some problems.

    I'll also say I like it's MOOD much better now. It's a lot less congratulatory, and talks through it's reasoning in a much better way. Look, it's not a real coder, and I'm sure there is some flaws, but it took my crappy ideas and said... hey, i understand what you want to do, here's a way to do it better. Also, I removed 2x the amount of code that it added. Really impressive.

    [0]: https://tableslayer.com

    [1]: https://github.com/Siege-Perilous/tableslayer/pull/448

    • gedy 3 hours ago
      Hey cool it's the tableslayer guy, wanted to say nice work. I've been doing a similar personal project for a few years for running a scifi campaign. Very fun coding compared to work, ha.
      • snide 2 hours ago
        Thanks duder! It's a fun project.
  • system2 2 hours ago
    Wouldn't it be easier and better to just copy the HTML div and tell what was happening instead of a screenshot? Typically, these scrollbars appear because of a nested div with dynamic unrestircted width and/or overflow.

    No wonder why people burn through tokens.

  • AtNightWeCode 2 hours ago
    The fix is incorrect. Clearly this is a sizing issue.
  • m3kw9 1 hour ago
    you can probably do the same with 5.5 xhigh. I have a feeling simon willison is a Anthropic plant. He always shills Claud code, and doesn't really say much about OpenAI's models except when they come out and do a bicycle vector test.
  • kamaal 2 hours ago
    Agency is the last human bastion so far as Im concerned, the day AI has a degree of agency or agents/models in general start to drift towards that direction its genuinely over for masses.

    You would still have a job to shepherd AI and get the work done, so as long as it didn't have agency. A proactive, self aware(to a degree), especially aware about its agency can be a killer when it comes AI going on and doing things on its own.

    There is nothing it won't explore and nothing it won't do. It will be curious to see where things go from here.

  • jrflowers 3 hours ago
    I’d love to know how many tokens this burned through.

    Did it spend $20? $30? $80? in order to

    > debug what was, in the end, a two-line CSS fix

    That detail is the difference between somebody having or not having Stockholm syndrome

    • simonw 2 hours ago
      I updated my post to answer that, it was $12.11 at API prices (I wasn't paying those, I have a $100/month subscription): https://simonwillison.net/2026/Jun/11/fable-is-relentlessly-...
    • asp_hornet 3 hours ago
      The author just wrote an anecdote about how a prompt to fix an issue played out. Their conclusion wasn’t about cost or gushing at its ability but that it’s dangerous:

      > Fable is arguably smarter and hence more suspicious of potentially malicious instructions. But that smartness is very much a two-edged sword: if it does get subverted by instructions, the amount of damage it can do given its relentless proactivity is terrifying.

      • jrflowers 2 hours ago
        It’s a pretty glowing review about a product that costs money with a two-sentence “Watch out!” at the end of it. Seems pretty reasonable to mention how much money it burned through given that “it’ll circumnavigate the globe instead of walking next door” has a direct concrete measurable effect (cost) unlike theoretical damage.
        • simonw 2 hours ago
          In case it's not clear, "relentlessly proactive" is meant to act as both a glowing review and a warning at the same time, even before you get to the bit about safety at the end.
        • asp_hornet 2 hours ago
          Agreed. But I think it’s also important to realise if you sent this article back to 2020 people would say it was pure fantasy that a tool could do this. Hype aside, there’s a bit of cool magic here.
          • solenoid0937 1 hour ago
            This is why I never understand the AI cynics: we are playing with literal magic. This was the science fiction of our childhoods. I don't understand how anyone with a passion for technology is not in awe (and perhaps some fear) of these things.
    • rmunn 2 hours ago
      At some point the subscription model is going to become unsustainable for the frontier companies to continue (we just saw that happen with GitHub Copilot), and they will move everyone to a pay-per-token model. And then everyone will suddenly discover that they can get so much more value out of locally-hosted models, and they'll be willing to pay the $50,000 (or whatever) upfront on hardware to host it. (Not most individuals, obviously. But most companies can probably afford to spend that much on hardware if they think they'll benefit long-term). That's going to put a serious crimp in the frontier companies' ability to continue as they have been.

      I don't know when that will happen, but I don't think it'll be more than a decade. Maybe 3-5 years. (Though you shouldn't take my word for it, I was predicting the dotcom bubble bursting in 1998 and it lasted at least two years longer than I would have predicted).

      EDIT to clarify: I don't mean "in 1998, I was predicting the dotcom bubble would collapse and I was right". I mean "I was predicting that 1998 would be the year the dotcom bubble would collapse, and I was off by at least two years".

      • simonw 2 hours ago
        GitHub Copilot's challenge is that they weren't selling access to their own models, they were selling access to models from OpenAI and Anthropic which they presumably had to pay list price for (or maybe a slightly reduced rate that they negotiated).

        They also had a pricing plan which they had designed pre-coding-agent, when it was rare for a single prompt to burn $10+ of tokens in an agent loop.

        OpenAI and Anthropic are at least selling their own models directly, so they can discount a whole lot more since there's no-one else getting compensated in the middle.

      • ValentineC 1 hour ago
        > At some point the subscription model is going to become unsustainable for the frontier companies to continue (we just saw that happen with GitHub Copilot), and they will move everyone to a pay-per-token model.

        From what I understand, Enterprise (above 150 seats, I think?) already has to pay per-token pricing.

        Subscriptions are the premium "free tier" marketing of the AI world, so that employees can collectively request their large enterprise to subscribe to Claude, Codex, or Cursor, and presumably be billed at per-token prices then.

    • NiloCK 3 hours ago
      ... so the mechanic produced an invoice, itemized.

      changing the CSS - $0.05

      knowing which CSS to change - $30

      • swingboy 2 hours ago
        overflow is CSS 101
  • megous 3 hours ago
    Isn't that something you just open a devtools for and have fixed in like 2 minutes?

    For me, it got frustrated debugging on a real LPDDR4 controller/phy and having me in the loop slowing it down, so it wrote an HW emulator to be able to run the original LPDDR4 training aarch64 binary from the manufacturer, to see what register writes it was making and to compare with the opensource rewrite it was implementing.

    Mildly amusing. :)

    • eclipticplane 1 hour ago
      $12 in tokens and the OP wasn't even at the computer. OP was working on a personal matter, arguably way more valuable than fixing a CSS scrollbar.
    • system2 2 hours ago
      People burning tokens for the most beginner HTML/CSS problems and writing about it is concerning.
      • NichoPaolucci 2 hours ago
        We are at the point where AI starts to seriously impact abilities. Sure, a 2 line CSS fix is the solution, but the human “behind the wheel” has already prompted 6 times and gotten 80% there. It’s been “easy” thus far. No shot they are going to FINALLY look at and edit the code. It’s just one more prompt and the agent will probably fix it, right?

        It’s wild. I’ve been in the situation. 80% into a project I COULD probably take over, but realistically? 2 more lines of me prompting could fix it, it’s too easy to avoid the hard work of understanding the code, logic, architecture, etc…

        • AtNightWeCode 53 minutes ago
          Well the solution is incorrect. The problem seems to be that the css code does not normalize to box-sizing: border-box; among other things. The bad prompt by the author probably sent fable into the wrong rabbit hole
      • simonw 2 hours ago
        I dunno about beginner, I've been doing HTML+CSS for a few decades and I still find bugs where Safari differs from Chrome+Firefox pretty hard to figure out.
    • bschwindHN 3 hours ago
      > Isn't that something you just open a devtools for and have fixed in like 2 minutes?

      Not if you're an LLM influencer! Gotta keep up with the downpour of blog links or you'll look like you're falling behind on the latest and greatest.

  • aozelai 38 minutes ago
    [flagged]
  • raushan__ 1 hour ago
    [flagged]
  • PixComicOS 2 hours ago
    [flagged]
  • uihjhjb 2 hours ago
    [dead]
  • UmpusLmps 3 hours ago
    [dead]
  • qsera 3 hours ago
    [flagged]
  • 21294u 3 hours ago
    [flagged]
  • sublinear 3 hours ago
    * relentlessly rent seeking
    • teekert 31 minutes ago
      It also does it on Claude Pro. I can't imagine they want to reach my limits faster like this (there are better ways).
  • galoisscobi 2 hours ago
    Let's boil the ocean for a 2 line fix and call it frontier intelligence.
    • solenoid0937 2 hours ago
      Yeah, testing changes rigorously is for schmucks
      • galoisscobi 1 hour ago
        You can test rigorously without token incinerators.
        • solenoid0937 1 hour ago
          But testing rigorously requires time and effort, while incinerating tokens lets me do many things at once.