I don't know about avoided, this kind of represents the WTF per minute code quality measurement. When I write WTF as a response to Claude, I would actually love if an Antrhopic engineer would take a look at what mess Claude has created.
Why do you need to do it at the client side? You are leaking so much information on the client side.
And considering the speed of Claude code, if you really want to do on the client side, a few seconds won't be a big deal.
It's fast, but it'll miss a ton of cases. This feels like it would be better served by a prompt instruction, or an additional tiny neural network.
And some of the entries are too short and will create false positives. It'll match the word "offset" ("ffs"), for example. EDIT: no it won't, I missed the \b. Still sounds weird to me.
The pattern only matches if both ends are word boundaries. So "diffs" won't match, but "Oh, ffs!" will. It's also why they had to use the pattern "shit(ty|tiest)" instead of just "shit".
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.
It's not hard to find them, they are in clear text in the binary, you can search for known ones with grep and find the rest nearby. You could even replace them inplace (but now its configurable).
Random aside: I've seen a 2015 game be accused of AI slop on Steam because it used a similar concept... And mind you, there's probably thousands of games that do this.
First it was punctuation and grammar, then linguistic coherence, and now it's tiny bits of whimsy that are falling victim to AI accusations. Good fucking grief
To me, this is a sign of just how much regular people do not want AI. This is worse than crypto and metaverse before it. Crypto, people could ignore and the dumb ape pictures helped you figure out who to avoid. Metaverse, some folks even still enjoyed VR and AR without the digital real estate bullshit. And neither got shoved down your throat in everyday, mundane things like writing a paper in Word or trying to deal with your auto mechanic.
But AI is causing such visceral reactions that it's bleeding into other areas. People are so averse to AI they don't mind a few false positives.
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
But will this be released as a feature? For me it seems like it's an Anthropic internal tool to secretly contribute to public repositories to test new models etc.
You'll never win this battle, so why waste feelings and energy on it? That's where the internet is headed. There's no magical human verification technology coming to save us.
This is my pet peeve with LLMs, they almost always fails to write like a normal human would. Mentioning logs, or other meta-things which is not at all interesting.
Really surprising how many people are downplaying this leak!
"Google and OpenAi already open sourced their Agents, so this leak isn't that relevant " What Google and OpenAi have open sourced is their Agents SDK, a toolkit, not the secret sauce of how their flagship agents are wired under the hood!
expect the takedown hammer on the tweet, the R2 link, and any public repos soon
ANTI_DISTILLATION_CC
This is Anthropic's anti-distillation defence baked into Claude Code. When enabled, it injects anti_distillation: ['fake_tools'] into every API request, which causes the server to silently slip decoy tool definitions into the model's system prompt. The goal: if someone is scraping Claude Code's API traffic to train a competing model, the poisoned training data makes that distillation attempt less useful.
This is the single worst function in the codebase by every metric:
- 3,167 lines long (the file itself is 5,594 lines)
- 12 levels of nesting at its deepest
- ~486 branch points of cyclomatic complexity
- 12 parameters + an options object with 16 sub-properties
- Defines 21 inner functions and closures
- Handles: agent run loop, SIGINT, rate-limits, AWS auth, MCP lifecycle, plugin install/refresh, worktree bridging, team-lead polling (while(true) inside), control message dispatch (dozens of types), model switching, turn interruption
recovery, and more
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.
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.
I don’t think that’s a good comparison. There isn’t anything preventing Anthropic from, say, detecting whether the user is using the exact same system prompt and tool definition as Claude Code and call it a day. Will make developing other apps nearly impossible.
It’s a dynamic, subscription based service, not a static asset like a video.
It is a real product. They take real payments and deliver on whats promised.
Not sure if its an attempt to subvert criticism by using satirical language, or if they truly have so little respect for the open source community.
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.
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.
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.
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?
Gemini CLI and Codex are open source anyway. I doubt there was much of a moat there anyway. The cool kids are using things like https://pi.dev/ anyway.
They can't. AI 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.
I'm sure it's not _entirely_ built that way, and in practically speaking GitHub will almost certainly take it down rather than doing some kind of deep research about which code is which.
They do have a couple of interesting features that has not been publicly heard of yet:
Like KAIROS which seems to be like an inbuilt ai assistant and Ultraplan which seems to enable remote planning workflows, where a separate environment explores a problem, generates a plan, and then pauses for user approval before execution.
Not really, except that they have a bunch of weird things in the source code and people like to make fun of it. OpenCode/Codex generally doesn't have this since these are open-source projects from the get go.
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
Maybe the OP could clarify, I don't like reading leaked code, but I'm curious:
my understanding is that is it the source code for "claude code", the coding assistant that remotely calls the LLMs.
Is that correct ? The weights of the LLMs are _not_ in this repo, right ?
It sure sucks for anthropic to get pawned like this, but it should not affect their bottom line much ?
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.
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.
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
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.
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.
LLMs are good in JS and Python which means everything from now on will be written in or ported to either of those two languages.
So yeah, JS is the future of all software.
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.
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.
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.
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].
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.
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.
“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.
Code quality no longer carries the same weight as it did pre LLMs. It used to matter becuase humans were the ones reading/writing it so you had to optimize for readability and maintainability. But these days what matters is the AI can work with it and you can reliably test it. Obviously you don’t want code quality to go totally down the drain, but there is a fine balance.
Optimize for consistency and a well thought out architecture, but let the gnarly looking function remain a gnarly function until it breaks and has to be refactored. Treat the functions as black boxes.
Personally the only time I open my IDE to look at code, it’s because I’m looking at something mission critical or very nuanced. For the remainder I trust my agent to deliver acceptable results.
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.
It’s not a particularly sophisticated tool. I’d put my money on one experienced engineer being able to achieve the same functionality in 3-6 months (even without the vibe coding).
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
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...
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
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.
That's exactly why, access to global mutable state should be limited to as small a surface area as possible, so 99% of code can be locally deterministic and side-effect free, only using values that are passed into it. That makes testing easier too.
environment variables can change while the process is running and are not memory safe (though I suspect node tries to wrap it with a lock). Meaning if you check a variable at point A, enter a branch and check it again at point B ... it's not guaranteed that they will be the same value. This can cause you to enter "impossible conditions".
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).
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 is a client running on an interpreted language your own computer, there is nothing to secure or hide as source was provided to you already or am I mistaking?
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.
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...
I don't know about avoided, this kind of represents the WTF per minute code quality measurement. When I write WTF as a response to Claude, I would actually love if an Antrhopic engineer would take a look at what mess Claude has created.
An LLM company using regexes for sentiment analysis? That's like a truck company using horses to transport parts. Weird choice.
Because they want it to be executed quickly and cheaply without blocking the workflow? Doesn’t seem very weird to me at all.
Why do you need to do it at the client side? You are leaking so much information on the client side. And considering the speed of Claude code, if you really want to do on the client side, a few seconds won't be a big deal.
They probably have statistics on it and saw that certain phrases happen over and over so why waste compute on inference.
I used regexes in a similar way but my implementation was vibecoded, hmmm, using your analysis Claude Code writes code by hand.
what you are suggesting would be like a truck company using trucks to move things within the truck
That’s what they do. Ever heard of a hand truck?
Do we have a hand llm perchance?
I never knew the name of that device.
Thanks
Good to have more than a hammer in your toolbox!
They're searching for multiple substrings in a single pass, regexes are the optimal solution for that.
The issue isn't that regex are a solution to find a substring. The issue is that you shouldn't be looking for substrings in the first place.
This has buttbuttin energy. Welcome to the 80s I guess.
Very likely vibe coded.
I've seen Claude Code went with a regex approach for a similar sentiment-related task.
It's fast, but it'll miss a ton of cases. This feels like it would be better served by a prompt instruction, or an additional tiny neural network.
And some of the entries are too short and will create false positives. It'll match the word "offset" ("ffs"), for example. EDIT: no it won't, I missed the \b. Still sounds weird to me.
It’s fast and it matches 80% of the cases. There’s no point in overengineering it.
The pattern only matches if both ends are word boundaries. So "diffs" won't match, but "Oh, ffs!" will. It's also why they had to use the pattern "shit(ty|tiest)" instead of just "shit".
You're right, I missed the \b's. Thanks for the correction.
Ridiculous string comparisons on long chains of logic are a hallmark of vibe-coding.
Glad abusing words in my list are not in that. but its surprising that they use regex for sentiments.
If anyone at anthropic is reading this and wants more logs from me add jfc.
Yeah, this is crazy
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.
Finally all spinner verbs revealed: https://github.com/instructkr/claude-code/blob/main/src/cons...
It's not hard to find them, they are in clear text in the binary, you can search for known ones with grep and find the rest nearby. You could even replace them inplace (but now its configurable).
Random aside: I've seen a 2015 game be accused of AI slop on Steam because it used a similar concept... And mind you, there's probably thousands of games that do this.
First it was punctuation and grammar, then linguistic coherence, and now it's tiny bits of whimsy that are falling victim to AI accusations. Good fucking grief
To me, this is a sign of just how much regular people do not want AI. This is worse than crypto and metaverse before it. Crypto, people could ignore and the dumb ape pictures helped you figure out who to avoid. Metaverse, some folks even still enjoyed VR and AR without the digital real estate bullshit. And neither got shoved down your throat in everyday, mundane things like writing a paper in Word or trying to deal with your auto mechanic.
But AI is causing such visceral reactions that it's bleeding into other areas. People are so averse to AI they don't mind a few false positives.
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
Undercover mode also pretends to be human, which I'm less ok with:
https://github.com/chatgptprojects/claude-code/blob/642c7f94...
But will this be released as a feature? For me it seems like it's an Anthropic internal tool to secretly contribute to public repositories to test new models etc.
I don't care who is using it, I don't want LLMs pretending to be humans in public repos. Anthropic just lost some points with me for this one.
EDIT: I just realized this might be used without publishing the changes, for internal evaluation only as you mentioned. That would be a lot better.
You'll never win this battle, so why waste feelings and energy on it? That's where the internet is headed. There's no magical human verification technology coming to save us.
This is my pet peeve with LLMs, they almost always fails to write like a normal human would. Mentioning logs, or other meta-things which is not at all interesting.
> Write commit messages as a human developer would — describe only what the code change does.
The undercover mode prompt was generated using AI.
That whole “feature” is vile.
(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.
You heard it here first
So close to April Fool's too. I'm sure it will still be a surprise for a majority of their users.
Really surprising how many people are downplaying this leak! "Google and OpenAi already open sourced their Agents, so this leak isn't that relevant " What Google and OpenAi have open sourced is their Agents SDK, a toolkit, not the secret sauce of how their flagship agents are wired under the hood! expect the takedown hammer on the tweet, the R2 link, and any public repos soon
I'm tempted to /init but can any sober (and smarter) individuals tell me why this is or isn't a good idea?
src/cli/print.ts
This is the single worst function in the codebase by every metric:
This should be at minimum 8–10 separate modules.Yes, if it was made for human comprehension or maintenance.
If it's entirely generated / consumed / edited by an LLM, arguably the most important metric is... test coverage, and that's it ?
Can't we have generated / llm generated code to be more human maintainable?
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/
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.
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.
I don’t think that’s a good comparison. There isn’t anything preventing Anthropic from, say, detecting whether the user is using the exact same system prompt and tool definition as Claude Code and call it a day. Will make developing other apps nearly impossible.
It’s a dynamic, subscription based service, not a static asset like a video.
Just use one of the distilled claude clones instead https://x.com/0xsero/status/2038021723719688266?s=46
"Approach Sonnet"...
So not even close to Opus, then?
These are a year behind, if not more. And they're probably clunky to use.
Could you use claude via aws bedrock?
Malus is not a real project btw, it's a parody:
“Let's end open source together with this one simple trick”
https://pretalx.fosdem.org/fosdem-2026/talk/SUVS7G/feedback/
Malus is translating code into text, and from text back into code.
It gives the illusion of clean room implementation that some companies abuse.
The irony is that ChatGPT/Claude answers are all actually directly derived from open-source code, so...
They accept real money though.
https://www.youtube.com/watch?v=6godSEVvcmU
I love the irony on seeing the contribution counter at 0
Who'd have thought, the audience who doesn't want to give back to the opensource community, giving 0 contributions...
It reads attribution really?
Oh god, I was so close to believing Malus was a real product and not satire.
Yeah... look again.
https://www.youtube.com/watch?v=6godSEVvcmU
It is a real product. They take real payments and deliver on whats promised. Not sure if its an attempt to subvert criticism by using satirical language, or if they truly have so little respect for the open source community.
For a combo with another HN homepage story, Claude Code uses… Axios: https://x.com/icanvardar/status/2038917942314778889?s=20
https://news.ycombinator.com/item?id=47582220
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.
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.
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.
You are not allowed to use the assistance of Claude to manufacture hacks and bombs on your computer
This is neither.
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.
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?
Your favorite LLM is great at building a super buggy renderer, so that's no longer a moat
Gemini CLI and Codex are open source anyway. I doubt there was much of a moat there anyway. The cool kids are using things like https://pi.dev/ anyway.
Was searching for the rumored Mythos/Capybara release, and what even is this file? https://github.com/chatgptprojects/claude-code/blob/642c7f94...
Also saw this on twitter earlier, thought someone was just making a fake hype post thing. But turns out to be an actual prompt for capybara huh: https://github.com/chatgptprojects/claude-code/blob/642c7f94...
turns out its for an April fools tomorrow: https://x.com/mesmerlord/status/2038938888178135223
Source here https://github.com/chatgptprojects/claude-code/
https://github.com/instructkr/claude-code
this one has more stars and more popular
won't they just try to dmca or take these down especially if they're more popular
Which is why you should clone it right now
They can't. AI 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.
I'm sure it's not _entirely_ built that way, and in practically speaking GitHub will almost certainly take it down rather than doing some kind of deep research about which code is which.
Given that from 2026 onwards most of the code is going to be computer generated, doesn't it open some interesting implications there ?
They do have a couple of interesting features that has not been publicly heard of yet:
Like KAIROS which seems to be like an inbuilt ai assistant and Ultraplan which seems to enable remote planning workflows, where a separate environment explores a problem, generates a plan, and then pauses for user approval before execution.
Is there anything special here vs. OpenCode or Codex?
There were/are a lot of discussions on how the harness can affect the output.
Not really, except that they have a bunch of weird things in the source code and people like to make fun of it. OpenCode/Codex generally doesn't have this since these are open-source projects from the get go.
(I work on OpenCode)
Once the USA wakes up, this will be insane news
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?
LoL! https://news.ycombinator.com/item?id=30337690
Not exactly this, but close.
> 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.
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
interesting to see cost-tracker.ts in there. makes you wonder why they track usage internally but don't surface it to users in any meaningful way
400k lines of code per scc
Maybe the OP could clarify, I don't like reading leaked code, but I'm curious: my understanding is that is it the source code for "claude code", the coding assistant that remotely calls the LLMs.
Is that correct ? The weights of the LLMs are _not_ in this repo, right ?
It sure sucks for anthropic to get pawned like this, but it should not affect their bottom line much ?
> I don't like reading leaked code
Don't worry about that, the code in that repository isn't Anthropic's to begin with.
Yes it's the claude code CLI tool / coding agent harness, not the weights.
This code hasn't been open source until now and contains information like the system prompts, internal feature flags, etc.
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.
In the app, it now reads:
> current: 2.1.88 · latest: 2.1.87
Which makes me think they pulled it - although it still shows up as 2.1.88 on npmjs for now (cached?).
Too little to late. Someone has it building now.
https://github.com/oboard/claude-code-rev
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.
> The source code of the slot machine is not relevant to the casino manager.
Famously code leaks/reverse engineering attempts of slot machines matter enormously to casino managers
[0] -https://en.wikipedia.org/wiki/Ronald_Dale_Harris#:~:text=Ron...
[1] - https://cybernews.com/news/software-glitch-loses-casino-mill...
[2] - https://sccgmanagement.com/sccg-news/2025/9/24/superbet-pays...
https://xcancel.com/Fried_rice/status/2038894956459290963
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
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.
haha.. Anthropic need to hire fixer from vibecodefixers.com to fix all that messy code..lol
I am waiting now for someone to make it work with a Copilot Pro subscription.
does this not work? https://www.mintlify.com/samarth777/claude-code-copilot/intr...
I believe GitHub can and does suspend account that use such proxies.
Isn't it open source?
Or is there an open source front-end and a closed backend?
> 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.
No, it was never open source. You could always reverse engineer the cli app but you didn't have access to the source.
The Github repo is only for issue tracker
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.
You may have mistaken it with Codex
https://github.com/openai/codex
No
Why is Claude Code, a desktop tool, written in JS? Is the future of all software JS or Typescript?
Original author of Claude Code is expert on TypeScript [1]
[1] https://www.amazon.com/Programming-TypeScript-Making-JavaScr...
LLMs are good in JS and Python which means everything from now on will be written in or ported to either of those two languages. So yeah, JS is the future of all software.
I am happy you woke up from your 10 year coma.
It's not a desktop tool, it's a CLI tool.
But a lot of desktop tools are written in JS because it's easy to create multi-platform applications.
Because it's the most popular programming language in the world?
The code looks, at a glance, as bad as you expect.
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.
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.
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.
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
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.
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.
“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.
Code quality no longer carries the same weight as it did pre LLMs. It used to matter becuase humans were the ones reading/writing it so you had to optimize for readability and maintainability. But these days what matters is the AI can work with it and you can reliably test it. Obviously you don’t want code quality to go totally down the drain, but there is a fine balance.
Optimize for consistency and a well thought out architecture, but let the gnarly looking function remain a gnarly function until it breaks and has to be refactored. Treat the functions as black boxes.
Personally the only time I open my IDE to look at code, it’s because I’m looking at something mission critical or very nuanced. For the remainder I trust my agent to deliver acceptable results.
Honestly when using it, it feels vibe coded to the bone, together with the matching weird UI footgun quirks
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.
It’s not a particularly sophisticated tool. I’d put my money on one experienced engineer being able to achieve the same functionality in 3-6 months (even without the vibe coding).
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
Can you give an example? Looks fairly decent to me
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
I always write code like that. I don't like early returns. This approximates `if` statements being an expression that returns something.
[delayed]
> Why even use else if with return...
What is the problem with that? How would you write that snippet? It is common in the new functional js landscape, even if it is pass-by-ref.
Using guard clauses. Way more readable and easy to work with.
I'm not that familiar with TypeScript/JavaScript - what would be a proper way of handling complex logic? Switch statements? Decision tables?
Fits with the origin story of Claude Code...
insert "AI is just if statements" meme
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...
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
Lol even the name is crazy
have a look at src/bootstrap/state.ts :D
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.
> process.env? It is a global map
That's exactly why, access to global mutable state should be limited to as small a surface area as possible, so 99% of code can be locally deterministic and side-effect free, only using values that are passed into it. That makes testing easier too.
environment variables can change while the process is running and are not memory safe (though I suspect node tries to wrap it with a lock). Meaning if you check a variable at point A, enter a branch and check it again at point B ... it's not guaranteed that they will be the same value. This can cause you to enter "impossible conditions".
For one it's harder to unit test.
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).
It probably exists only in CLAUDE or AGENTS.md since no humans are working on the code!
You're right about process.argv - wow, that looks like a maintenance and testability nightmare.
They use claude code to code it. Makes sense
Nothing a couple /simplify's can't take care of.
I hope everyone provides excellent feedback so they improve Claude Code.
I guess it's time for Anthropic to open source Claude Code.
And while they are at it, open source Opus and Sonet. :)
I wonder what will happen with the poor guy who forgot to delete the code...
Ha. I'm surprised it's not a CI job
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?
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.
It is a client running on an interpreted language your own computer, there is nothing to secure or hide as source was provided to you already or am I mistaking?
It was heavily obfuscated, keeping users in the dark about what they’re installing and running.
It is a client running on an interpreted language your own computer, there is nothing to secure or hide as source is provided to you already.
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.
If it was included unintentionally, then it's a leak.
The only exciting leak would be the Opus weights themselves.
The source is linked to in this thread. Is that not the source code?