30 comments

  • bkryza 19 minutes ago
    They have an interesting regex for detecting negative sentiment in users prompt which is then logged (explicit content): https://github.com/chatgptprojects/claude-code/blob/642c7f94...

    I guess these words are to be avoided...

    • nodja 1 minute ago
      If anyone at anthropic is reading this and wants more logs from me add jfc.
    • raihansaputra 8 minutes ago
      i wish that's for their logging/alert. i definitely gauge model's performance by how much those words i type when i'm frustrated in driving claude code.
  • treexs 1 hour ago
    The big loss for Anthropic here is how it reveals their product roadmap via feature flags. A big one is their unreleased "assistant mode" with code name kairos.

    Just point your agent at this codebase and ask it to find things and you'll find a whole treasure trove of info.

    Edit: some other interesting unreleased/hidden features

    - The Buddy System: Tamagotchi-style companion creature system with ASCII art sprites

    - Undercover mode: Strips ALL Anthropic internal info from commits/PRs for employees on open source contributions

    • avaer 1 hour ago
      (spoiler alert)

      Buddy system is this year's April Fool's joke, you roll your own gacha pet that you get to keep. There are legendary pulls.

      They expect it to go viral on Twitter so they are staggering the reveals.

      • JohnLocke4 30 minutes ago
        You heard it here first
      • ares623 25 minutes ago
        So close to April Fool's too. I'm sure it will still be a surprise for a majority of their users.
    • ben8bit 1 hour ago
      [dead]
  • avaer 1 hour ago
    Would be interesting to run this through Malus [1] or literally just Claude Code and get open source Claude Code out of it.

    I jest, but in a world where these models have been trained on gigatons of open source I don't even see the moral problem. IANAL, don't actually do this.

    https://malus.sh/

    • NitpickLawyer 1 hour ago
      The problem is the oauth and their stance on bypassing that. You'd want to use your subscription, and they probably can detect that and ban users. They hold all the power there.
      • avaer 1 hour ago
        You'd be playing cat and mouse like yt-dlp, but there's probably more value to this code than just a temporary way to milk claude subscriptions.
      • woleium 1 hour ago
        Just use one of the distilled claude clones instead https://x.com/0xsero/status/2038021723719688266?s=46
        • echelon 23 minutes ago
          "Approach Sonnet"...

          So not even close to Opus, then?

          These are a year behind, if not more. And they're probably clunky to use.

      • pkaeding 34 minutes ago
        Could you use claude via aws bedrock?
  • lukan 53 minutes ago
    Neat. Coincidently recently I asked Claude about Claude CLI, if it is possible to patch some annoying things (like not being able to expand Ctrl + O more than once, so never be able to see some lines and in general have more control over the context) and it happily proclaimed it is open source and it can do it ... and started doing something. Then I checked a bit and saw, nope, not open source. And by the wording of the TOS, it might brake some sources. But claude said, "no worries", it only break the TOS technically. So by saving that conversation I would have some defense if I would start messing with it, but felt a bit uneasy and stopped the experiment. Also claude came into a loop, but if I would point it at this, it might work I suppose.
    • mikrotikker 17 minutes ago
      I think that you do not need to feel uneasy at all. It is your computer and your memory space that the data is stored and operating in you can do whatever you like to the bits in that space. I would encourage you to continue that experiment.
      • lukan 9 minutes ago
        Well, the thing is I do not just use my computer, but connect to their computers and I do not like to get banned. I suppose simple UI things like expanding source files won't change a thing, but the more interesting things, editing the context etc. do have that risk, but no idea if they look for it or enforce it. Their side is, if I want to have full control, I need to use the API directly(way more expensive) and what I want to do is basically circumventing it.
      • singularity2001 13 minutes ago
        You are not allowed to use the assistance of Claude to manufacture hacks and bombs on your computer
  • Squarex 56 minutes ago
    Codex and gemini cli are open source already. And plenty of other agents. I don't think there is any moat in claude code source.
    • rafram 49 minutes ago
      Well, Claude does boast an absolutely cursed (and very buggy) React-based TUI renderer that I think the others lack! What if someone steals it and builds their own buggy TUI app?
      • loveparade 35 minutes ago
        Your favorite LLM is great at building a super buggy renderer, so that's no longer a moat
  • mesmertech 14 minutes ago
    Was searching for the rumored Mythos/Capybara release, and what even is this file? https://github.com/chatgptprojects/claude-code/blob/642c7f94...
  • dheerajmp 1 hour ago
    • zhisme 19 minutes ago
      https://github.com/instructkr/claude-code

      this one has more stars and more popular

      • treexs 18 minutes ago
        won't they just try to dmca or take these down especially if they're more popular
        • panny 9 minutes ago
          They can't. Computer generated code cannot be copyrighted. They've stated that claude code is built with claude code. You can take this and start your own claude code project now if you like. There's zero copyright protection on this.
  • karimf 1 hour ago
    Is there anything special here vs. OpenCode or Codex?

    There were/are a lot of discussions on how the harness can affect the output.

  • cbracketdash 28 minutes ago
    Once the USA wakes up, this will be insane news
    • echelon 18 minutes ago
      What's special about Claude Code? Isn't Opus the real magic?

      Surely there's nothing here of value compared to the weights except for UX and orchestration?

      Couldn't this have just been decompiled anyhow?

  • Diablo556 5 minutes ago
    haha.. Anthropic need to hire fixer from vibecodefixers.com to fix all that messy code..lol
  • dhruv3006 48 minutes ago
    I have a feeling this is like llama.

    Original llama models leaked from meta. Instead of fighting it they decided to publish them officially. Real boost to the OS/OW models movement, they have been leading it for a while after that.

    It would be interesting to see that same thing with CC, but I doubt it'll ever happen.

  • jedisct1 4 minutes ago
    It shows that a company you and your organization are trusting with your data, and allowing full control over your devices 24/7, is failing to properly secure its own software.

    It's a wake up call.

  • bob1029 1 hour ago
    Is this significant?

    Copilot on OAI reveals everything meaningful about its functionality if you use a custom model config via the API. All you need to do is inspect the logs to see the prompts they're using. So far no one seems to care about this "loophole". Presumably, because the only thing that matters is for you to consume as many tokens per unit time as possible.

    The source code of the slot machine is not relevant to the casino manager. He only cares that the customer is using it.

    • esseph 1 hour ago
      > The source code of the slot machine is not relevant to the casino manager.

      Now do you want the list of the people it would be relevant to?

      People playing the game, criminals, auditors that could shut the casino down and/or fine them.

      Much bigger pool of people.

  • theanonymousone 55 minutes ago
    I am waiting now for someone to make it work with a Copilot Pro subscription.
  • vbezhenar 1 hour ago
    LoL! https://news.ycombinator.com/item?id=30337690

    Not exactly this, but close.

    • ivanjermakov 30 minutes ago
      > It exposes all your frontend source code for everyone

      I hope it's a common knowledge that _any_ client side JavaScript is exposed to everyone. Perhaps minimized, but still easily reverse-engineerable.

      • Monotoko 27 minutes ago
        Very easily these days, even if minified is difficult for me to reverse engineer... Claude has a very easy time of finding exactly what to patch to fix something
  • mapcars 1 hour ago
    Are there any interesting/uniq features present in it that are not in the alternatives? My understanding is that its just a client for the powerful llm
    • swimmingbrain 1 hour ago
      From the directory listing having a cost-tracker.ts, upstreamproxy, coordinator, buddy and a full vim directory, it doesn't look like just an API client to me.
  • bryanhogan 1 hour ago
  • ChicagoDave 47 minutes ago
    I hope everyone provides excellent feedback so they improve Claude Code.
  • LeoDaVibeci 1 hour ago
    Isn't it open source?

    Or is there an open source front-end and a closed backend?

    • dragonwriter 1 hour ago
      > Isn't it open source?

      No, its not even source available,.

      > Or is there an open source front-end and a closed backend?

      No, its all proprietary. None of it is open source.

    • avaer 1 hour ago
      No, it was never open source. You could always reverse engineer the cli app but you didn't have access to the source.
    • karimf 1 hour ago
      The Github repo is only for issue tracker
      • matheusmoreira 57 minutes ago
        Wow it's true. Anthropic actually had me fooled. I saw the GitHub repository and just assumed it was open source. Didn't look at the actual files too closely. There's pretty much nothing there.

        So glad I took the time to firejail this thing before running it.

    • agluszak 1 hour ago
      You may have mistaken it with Codex

      https://github.com/openai/codex

    • yellow_lead 1 hour ago
      No
  • anhldbk 54 minutes ago
    I guess it's time for Anthropic to open source Claude Code.
    • DeathArrow 48 minutes ago
      And while they are at it, open source Opus and Sonet. :)
  • q3k 1 hour ago
    The code looks, at a glance, as bad as you expect.
    • tokioyoyo 46 minutes ago
      It really doesn’t matter anymore. I’m saying this as a person who used to care about it. It does what it’s generally supposed to do, it has users. Two things that matter at this day and age.
      • noosphr 20 minutes ago
        Maybe if they cared a bit more they wouldn't have leaked the entire source code of their app.

        But what do I know. Code has been solved.

      • samhh 32 minutes ago
        It may be economically effective but such heartless, buggy software is a drain to use. I care about that delta, and yes this can be extrapolated to other industries.
        • tokioyoyo 26 minutes ago
          Genuinely I have no idea what you mean by buggy. Sure there are some problems here and there, but my personal threshold for “buggy” is much higher. I guess, for a lot of other people as well, given the uptake and usage.
      • FiberBundle 35 minutes ago
        This is the dumbest take there is about vibe coding. Claiming that managing complexity in a codebase doesn't matter anymore. I can't imagine that a competent engineer would come to the conclusion that managing complexity doesn't matter anymore. There is actually some evidence that coding agents struggle the same way humans do as the complexity of the system increases [0].

        [0] https://arxiv.org/abs/2603.24755

        • tokioyoyo 23 minutes ago
          I agree, there is obviously “complete burning trash” and there’s this. Ant team has got a system going on for them where they can still extend the codebase. When time comes to it, I’m assuming they would be able to rewrite as feature set would be more solid and assuming they’ve been adding tests as well.

          Reverse-engineering through tests have never been easier, which could collapse the complexity and clean the code.

      • hrmtst93837 26 minutes ago
        Users stick around on inertia until a failure costs them money or face. A leaked map file won't sink a tool on its own, but it does strip away the story that you can ship sloppy JS build output into prod and still ask people to trust your security model.

        'It works' is a low bar. If that's the bar you set you are one bad incident away from finding out who stayed for the product and who stayed because switching felt annoying.

        • tokioyoyo 21 minutes ago
          “It works and it’s doing what it’s supposed to do” encompasses the idea that it’s also not doing what it’s not supposed to do.

          Also “one bad incident away” never works in practice. The last two decades have shown how people will use the tools that get the job done no matter what kinda privacy leaks, destructive things they have done to the user.

    • breppp 46 minutes ago
      Honestly when using it, it feels vibe coded to the bone, together with the matching weird UI footgun quirks
      • tokioyoyo 45 minutes ago
        Team has been extremely open how it has been vibe coded from day 1. Given the insane amount of releases, I don’t think it would be possible without it.
        • breppp 8 minutes ago
          I don't really care about the code being an unmaintainable mess, but as a user there are some odd choices in the flow which feel could benefit from human judgement
    • loevborg 1 hour ago
      Can you give an example? Looks fairly decent to me
      • Insensitivity 1 hour ago
        the "useCanUseTool.tsx" hook, is definitely something I would hate seeing in any code base I come across.

        It's extremely nested, it's basically an if statement soup

        `useTypeahead.tsx` is even worse, extremely nested, a ton of "if else" statements, I doubt you'd look at it and think this is sane code

        • Overpower0416 45 minutes ago

            export function extractSearchToken(completionToken: {
              token: string;
              isQuoted?: boolean;
            }): string {
              if (completionToken.isQuoted) {
                // Remove @" prefix and optional closing "
                return completionToken.token.slice(2).replace(/"$/, '');
              } else if (completionToken.token.startsWith('@')) {
                return completionToken.token.substring(1);
              } else {
                return completionToken.token;
              }
            }
          
          Why even use else if with return...
        • luc_ 1 hour ago
          Fits with the origin story of Claude Code...
        • loevborg 1 hour ago
          useCanUseTool.tsx looks special, maybe it'scodegen'ed or copy 'n pasted? `_c` as an import name, no comments, use of promises instead of async function. Or maybe it's just bad vibing...
          • Insensitivity 1 hour ago
            Maybe, I do suspect _some_ parts are codegen or source map artifacts.

            But if you take a look at the other file, for example `useTypeahead` you'd see, even if there are a few code-gen / source-map artifacts, you still see the core logic, and behavior, is just a big bowl of soup

        • matltc 40 minutes ago
          Lol even the name is crazy
      • wklm 21 minutes ago
        have a look at src/bootstrap/state.ts :D
      • q3k 1 hour ago

          1. Randomly peeking at process.argv and process.env all around. Other weird layering violations, too.
          2. Tons of repeat code, eg. multiple ad-hoc implementations of hash functions / PRNGs.
          3. Almost no high-level comments about structure - I assume all that lives in some CLAUDE.md instead.
        • delamon 51 minutes ago
          What is wrong with peeking at process.env? It is a global map, after all. I assume, of course, that they don't mutate it.
          • q3k 5 minutes ago
            It's implicit state that's also untyped - it's just a String -> String map without any canonical single source of truth about what environment variables are consulted, when, why and in what form.

            Such state should be strongly typed, have a canonical source of truth (which can then be also reused to document environment variables that the code supports, and eg. allow reading the same options from configs, flags, etc) and then explicitly passed to the functions that need it, eg. as function arguments or members of an associated instance.

            This makes it easier to reason about the code (the caller will know that some module changes its functionality based on some state variable). It also makes it easier to test (both from the mechanical point of view of having to set environment variables which is gnarly, and from the point of view of once again knowing that the code changes its behaviour based on some state/option and both cases should probably be tested).

          • hu3 46 minutes ago
            For one it's harder to unit test.
        • s3p 52 minutes ago
          It probably exists only in CLAUDE or AGENTS.md since no humans are working on the code!
        • loevborg 1 hour ago
          You're right about process.argv - wow, that looks like a maintenance and testability nightmare.
          • darkstar_16 44 minutes ago
            They use claude code to code it. Makes sense
    • PierceJoy 59 minutes ago
      Nothing a couple /simplify's can't take care of.
  • DeathArrow 52 minutes ago
    I wonder what will happen with the poor guy who forgot to delete the code...
    • noosphr 20 minutes ago
      They aren't going to fire Claude, it's safe.
    • matltc 43 minutes ago
      Ha. I'm surprised it's not a CI job
    • epolanski 48 minutes ago
      Responsibility goes upwards.

      Why weren't proper checks in place in the first place?

      Bonus: why didn't they setup their own AI-assisted tools to harness the release checks?

  • isodev 42 minutes ago
    Can we stop referring to source maps as leaks? It was packaged in a way that wasn’t even obfuscated. Same as websites - it’s not a “leak” that you can read or inspect the source code.
    • echelon 17 minutes ago
      The only exciting leak would be the Opus weights themselves.
    • bmitc 17 minutes ago
      The source is linked to in this thread. Is that not the source code?
  • DeathArrow 45 minutes ago
    Why is Claude Code, a desktop tool, written in JS? Is the future of all software JS or Typescript?
  • mohsen1 0 minutes ago
    [dead]
  • cedws 29 minutes ago
    [dead]
  • mergeshield 1 hour ago
    [dead]
  • kevinbaiv 47 minutes ago
    [dead]
  • psihonaut 19 minutes ago
    [dead]
  • sixhobbits 49 minutes ago
    [dead]