The Claude Code Source Leak: fake tools, frustration regexes, undercover mode (alex000kim.com)

by alex000kim 578 comments 1376 points
Read article View on HN

578 comments

[−] d4rkp4ttern 44d ago
For me one of the most interesting aspects is how compaction works. It turns out compaction still preserves the full original pre-compaction conversation in the session jsonl file, and those are marked as "not to be sent to the API". Which means, even after compaction, if you think something was lost, you can tell CC to "look in the session log files to find details about what we did with XYZ". I knew this before the leak since it can be seen from the session logs. Some more details:

  The full conversation is preserved in the JSONL file, and messages
  are filtered before being sent to the API.

  Key mechanisms:

  1. JSONL is append-only — old pre-compaction messages are never deleted. New messages (boundary
  marker, summary, attachments) are appended after compaction.
  2. Messages have flags controlling API visibility:
    - isCompactSummary: true — marks the AI-generated summary message
    - isVisibleInTranscriptOnly: true — prevents a message from being sent to the API
    - isMeta — another filter for non-API messages
    - getMessagesAfterCompactBoundary() returns only post-compaction messages for API calls
  3. After compaction, the API sees only:
    - The compact boundary marker
    - The summary message
    - Attachments (file refs, plan, skills)
    - Any new messages after compaction
  4. Three compaction types exist:
    - Full compaction — API summarizes all old messages
    - Session memory compaction — uses extracted session memory as summary (cheaper)
    - Microcompaction — clears old tool result content when cache is cold (>1h idle)
[−] manwe150 44d ago
What is microcompaction? I didn’t realize there was any thing time based in CC, when I go eat dinner and come back it compacted while I was gone?
[−] d4rkp4ttern 43d ago
I dug into this more. It's disabled by default, and it's a cost/token-usage optimization.

  The logic is:

  1. Anthropic's API has a server-side prompt cache with a 1-hour TTL
  2. When you're actively using a session, each API call reuses the cached prefix — you only pay
  for new tokens
  3. After 1 hour idle, that cache is guaranteed expired
  4. Your next message will re-send and re-process the entire conversation from scratch — every
  token, full price
  5. So if you have 150K tokens of old Grep/Read/Bash outputs sitting in the conversation, you're
  paying to re-ingest all of that even though it's stale context the model probably doesn't need

  The microcompact says: "since we're paying full price anyway, let's shrink the bill by clearing
  the bulky stuff."

  What's preserved vs lost:
  - The tool_use blocks (what tool was called, with what arguments) — kept
  - The tool_result content (the actual output) — replaced with [Old tool result content cleared]
  - The most recent 5 tool results — kept

  So Claude can still see "I ran Grep for foo in src/" but not the 500-line grep output from 2
  hours ago.

  Does it affect quality? Yes, somewhat — but the tradeoff is that without it, you're paying
  potentially tens of thousands of tokens to re-ingest stale tool outputs that the model already
  acted on. And remember, if the conversation is long enough, full compaction would have summarized
   those messages anyway.

  And critically: this is disabled by default (enabled: false in timeBasedMCConfig.ts:31). It's
  behind a GrowthBook feature flag that Anthropic controls server-side. So unless they've flipped
  it on for your account, it's not happening to you.
[−] shreyssh 44d ago
[flagged]
[−] AceJohnny2 43d ago

>

it's basically a cost optimization masquerading as a feature

Cost optimization in the user's favor.

Remember that every time you send a new message to the LLM, you are actually sending the entire conversation again with that added last message to the LLM.

Remember that LLMs are fixed functions, the only variable is the context input (and temperature, sure).

Naively, this would lead to quadratic consumption of your token quota, which would get ridiculously expensive as conversations stretch into current 100k-1M context windows.

To solve this, AI providers cache the context on the GPU, and only charge you for the delta in the conversation/context. But they're not going to keep that GPU cache warm for you forever, so it'll time out after some inactivity.

So the microcompaction-on-idle happens to soften the token consumption blow after you've stepped away for lunch, your context cache has been flushed by the AI provider, and you basically have to spend tokens to restart your conversation from scratch.

[−] mzajc 45d ago
There are now several comments that (incorrectly?) interpret the undercover mode as only hiding internal information. Excerpts from the actual prompt[0]:

  NEVER include in commit messages or PR descriptions:
  - The phrase "Claude Code" or any mention that you are an AI
  - Co-Authored-By lines or any other attribution

  BAD (never write these):
  - 1-shotted by claude-opus-4-6
  - Generated with Claude Code
  - Co-Authored-By: Claude Opus 4.6 <…>
This very much sounds like it does what it says on the tin, i.e. stays undercover and pretends to be a human. It's especially worrying that the prompt is explicitly written for contributions to public repositories.

[0]: https://github.com/chatgptprojects/claude-code/blob/642c7f94...

[−] riedel 45d ago
No problem at all in the EU, as the user would either would need to review and redact the output or would need to put a transparency note up by law [0]. I am sure that Anthropic with their high ethical standards will educate their users ...

[0] https://ai-act-service-desk.ec.europa.eu/en/ai-act/article-5...

[−] mynameisvlad 45d ago
Since when is code considered

> which is published with the purpose of informing the public on matters of public interest

From your link, that's the only case where text needs to be attributed to AI.

[−] Orygin 44d ago
Code may not be, but opening a Merge Request undercover may be unlawful:

> Providers shall ensure that AI systems intended to interact directly with natural persons are designed and developed in such a way that the natural persons concerned are informed that they are interacting with an AI system

[−] mynameisvlad 44d ago
Then in that case you wouldn't be a provider. You are at best a deployer, and even then the definition doesn't exactly match using AI services.

That should be obvious considering an MR is not providing AI services.

[−] jonnybgood 44d ago
That merge request would be AI generated content. You wouldn't be interacting directly with the AI system that opened it.
[−] Orygin 44d ago
Depends if it's a closed loop agent. If the agent opens the request, writes the body and is triggered by an answer on the MR, then I'd expect the law to cover this.
[−] mynameisvlad 44d ago
What AI service are you providing with said MR?
[−] riedel 44d ago
Good question. Actually, i was assuming that at least source code is treated as text under the legal regime (there is typically special rules in copyright law, but provision applying to text should apply). Furthermore I would think pull requests, etc are all text. So I would think this applies.
[−] mynameisvlad 43d ago
But it's not just text. Once again, it's explicitly defined as:

> which is published with the purpose of informing the public on matters of public interest

There is no "informing public on matters of public interest" in source code nor an MR. It's clearly meant to prevent "deepfake" news, like the image and video ones explicitly call that out.

[−] riedel 43d ago
You are absolutely right. However, the recitals point clearly beyond only protection against fake news. IMHO running such an agent in stealth mode can easily be illegal, Articl 50 (1) states : > Providers shall ensure that AI systems intended to interact directly with natural persons are designed and developed in such a way that the natural persons concerned are informed that they are interacting with an AI system, unless this is obvious from the point of view of a natural person who is reasonably well-informed, observant and circumspect, taking into account the circumstances and the context of use.
[−] mynameisvlad 42d ago
But you aren't a provider of AI services by using AI. There's a clear difference already called out between "provider" and "deployer". An AI user could barely be called a "deployer" as is, let alone a "provider".

In other words, what AI service are you providing by creating a PR?

[−] riedel 39d ago
I would argue that the person reading an AI generated pull request is if there is no human oversight with an Ai. And are you sure that you get out of this definition (at least as a company):

> provider’ means a natural or legal person, public authority, agency or other body that develops an AI system or a general-purpose AI model or that has an AI system or a general-purpose AI model developed and places it on the market or puts the AI system into service under its own name or trademark, whether for payment or free of charge;

[−] mynameisvlad 37d ago
I would argue that an MR does none of those things.
[−] otterley 45d ago
I would have expected people (maybe a small minority, but that includes myself) to have already instructed Claude to do this. It’s a trivial instruction to add to your CLAUDE.md file.
[−] arcanemachiner 45d ago
It's a config setting (probably the same end result though):

https://code.claude.com/docs/en/settings#attribution-setting...

[−] tacone 45d ago
It doesn't work so well in my experience. I am currently wrapping (or asking the LLM to wrap) the commit message prompt in a script call.

   1. the LLM is instructed on how to write a commit message and never include co-authorship
   2. the LLM is asked to produce a commit message
   3. the LLM output is parsed by a script which removes co-authorship if the LLM chooses to include it nevertheless
[−] tacone 44d ago
Also for future reference, Copilot - specifically - includes a configuration flag to toggle the co-authorship (see copilot help config):

> includeCoAuthoredBy: whether to instruct the agent to add a Co-authored-by trailer to git commits; defaults to true.

This means that, if you don't explicitely configure otherwise, the LLM is specifically instructed to include co-authorship in its higher level instructions.

[−] dboreham 45d ago
I always assumed that if I tried to tell it, that it'd say "I'm sorry, Dave. I'm afraid I can't do that"
[−] schappim 45d ago
I guess our system prompt didn't work. If folks are having to add it manually into their own Claude.md files...
[−] schappim 45d ago
Typo from speech to text, corrected: “I guess Anthropic’s system prompt didn't work. If folks are having to add it manually into their own Claude.md files...”
[−] cfbradford 45d ago
Does this apply to their internal use as well? They can really only claim DMCA status on the leaked code if it was authored by humans. Claude attribution in their internal git history would make a strong case that they do not in fact own the copyright to Claude Code itself and are therefore abusing the DMCA system to protect leaked trade secrets rather than protect copyright.
[−] zgeor 44d ago
Genuine question: why can they only claim DMCA if the code is written by humans? Does DMCA specify the method of production?
[−] rainsil 44d ago
According to the US Copyright Office, fully AI-generated works aren’t eligible for copyright because they don’t have human authors. They’re in the public domain by default.

See: https://library.osu.edu/site/copyright/2026/02/06/artificial...

[−] pc86 44d ago
What constitutes "fully AI-generated" when you're in an edit loop between an agent and a human?
[−] justinclift 44d ago
It seems like it's an active area of legal thought (IANAL though).

Recent relevant discussion about this in the chardet repo between the chardet maintainer who relicensed the chardet code and Richard Fontana, a well regarded lawyer US IP lawyer who's worked for Red Hat (now IBM) for decades:

https://github.com/chardet/chardet/issues/334#issuecomment-4...

My take away from the conversation there is that being in an edit loop, where the files are AI generated through your control rather than directly editing the files yourself, means the files are then "AI authored" for copyright protection purposes rather than yourself.

But I double stress, I'm not a lawyer so may have misunderstood things radically.

[−] Eisenstein 44d ago
I think that may not be answerable until a case concerning it has been heard and ruled on. A lawyer may have a better answer for you, but if I had to bet then I'd put $100 on it being something like 'it depends'.
[−] VectorVault 44d ago
It's interesting how AI can be its own worst enemy in this legal system. The very thing it's excellent at is not protected. In practice, there seems to be a strong opportunity to disintermediate brands by acting as a layer of abstraction above the seller and manufacturer. An AI instruction likely cares less about brand or sharing customer information with the seller; it's just more friction and tokens spent.
[−] Eisenstein 44d ago
I think its just a case of dealing with something that has no precedent. We have never had to determine what the line is between a tool and an employee when they can both be instructed with natural language. If we were to evaluate AI as if it were in a contract with us for use of its time and efforts in exchange for something of consideration, it would be an easy ruling. If we were to evaluate AI as if it were a tool which operates as an extension of the operators skill without any independent additions then it would be an easy ruling. But since we now have a tool that can produce results that are independent of our ability to produce them with any former class of tools, then we have to create entirely new models for how to map these tools into the complexity of real life conflicts where people have different goals and where we must decouple fairness from intentions.
[−] zen928 45d ago
None of this is really worrying, this is a pattern implemented in a similar way by every single developer using AI to write commit messages after noticing how exceptionally noisy they are to self-attribute things. Anthropics views on AI safety and alignment with human interests dont suddenly get thrown out with the bathwater because of leaked internal tooling of which is functionally identical to a basic prompt in a mere interface (and not a model). I dont really buy all the forced "skepticism" on this thread tbh.
[−] petcat 45d ago
It's less about pretending to be a human and more about not inviting scrutiny and ridicule toward Claude if the code quality is bad. They want the real human to appear to be responsible for accepting Claud's poor output.
[−] andoando 45d ago
Ive seen it say coauthored by claude code on my prs...and I agree I dont want it to do that
[−] peacebeard 45d ago
The code has a stated goal of avoiding leaks, but then the actual implementation becomes broader than that. I see two possible explanations:

* The authors made the code very broad to improve its ability to achieve the stated goal

* The authors have an unstated goal

I think it's healthy to be skeptical but what I'm seeing is that the skeptics are pushing the boundaries of what's actually in the source. For example, you say "says on the tin" that it "pretends to be human" but it simply does not say that on the tin. It does say "Write commit messages as a human developer would" which is not the same thing as "Try to trick people into believing you're human." To convince people of your skepticism, it's best to stick to the facts.

[−] hombre_fatal 45d ago
You can already turn off "Co-Authored-By" via Claude Code config. This is what their docs show:

~/.claude/settings.json

    {
      "attribution": {
        "commit": "",
        "pr": ""
    },
The rest of the prompt is pretty clear that it's talking about internal use.

Claude Code users aren't the ones worried about leaking "internal model codenames" nor "unreleased model opus-4-8" nor Slack channel names. Though, nobody would want that crap in their generated docs/code anyways.

Seems like a nothingburger, and everyone seems to be fantasizing about "undercover mode" rather than engaging with the details.

[−] nateoda 45d ago
My first reaction is that they are using this to take advantage of OSS reviewers for in the wild evals.
[−] RA2lover 45d ago
There's a more worrying part: It refers to unreleased versions of Claude in more detail than released versions.

For a company calling chinese companies out for distillation attacks on their models, this very much looks like a distillation attack against human maintainers, especially when combined with the frustration detector.

[−] manbitesdog 45d ago
I cringe every time I see Claude trying to co-author a commit. The git history is expected to track accountability and ownership, not your Bill of Tools. Should I also co-author my PRs with my linter, intellisense and IDE?
[−] zem 44d ago
interesting, I still see "coauthored by..." messages put into my git commits (or was a couple of weeks ago at least)
[−] MeetRickAI 44d ago
[dead]
[−] shreyssh 44d ago
[flagged]
[−] sixtyj 45d ago
People make fun that we should say magic words in interaction with LLMs. How frustrated can Claude be? /s
[−] fatcullen 45d ago
The buddy feature the article mentions is planned for release tomorrow, as a sort of April Fools easter egg. It'll roll out gradually over the day for "sustained Twitter buzz" according to the source.

The pet you get is generated based off your account UUID, but the algorithm is right there in the source, and it's deterministic, so you can check ahead of time. Threw together a little app to help, not to brag but I got a legendary ghost https://claudebuddychecker.netlify.app/

[−] Reason077 45d ago

>

"Anti-distillation: injecting fake tools to poison copycats"

Plot twist: Chinese competitors end up developing real, useful versions of Claude's fake tools.

[−] geoffbp 45d ago
“Some bullet points are gated on process.env.USER_TYPE === 'ant' — Anthropic employees get stricter/more honest instructions than external use”

Interesting!

[−] autocracy101 45d ago
I made a visual guide for this https://ccunpacked.dev
[−] peacebeard 45d ago
The name "Undercover mode" and the line The phrase "Claude Code" or any mention that you are an AI sound spooky, but after reading the source my first knee-jerk reaction wouldn't be "this is for pretending to be human" given that the file is largely about hiding Anthropic internal information such as code names. I encourage looking at the source itself in order to draw your conclusions, it's very short: https://github.com/alex000kim/claude-code/blob/main/src/util...
[−] blcknight 45d ago
My GitHub fork of anthropics/claude-code just got taken down with a DMCA notice lol

It did not have a copy of the leaked code...

Anthropic thinking 1) they can unring this bell, and 2) removing forks from people who have contributed (well, what little you can contribute to their repo), is ridiculous.

---

DMCA: https://github.com/github/dmca/blob/master/2026/03/2026-03-3...

GitHub's note at the top says: "Note: Because the reported network that contained the allegedly infringing content was larger than one hundred (100) repositories, and the submitter alleged that all or most of the forks were infringing to the same extent as the parent repository, GitHub processed the takedown notice against the entire network of 8.1K repositories, inclusive of the parent repository."

[−] ripbozo 45d ago
I don't understand the part about undercover mode. How is this different from disabling claude attribution in commits (and optionally telling claude to act human?)

On that note, this article is also pretty obviously AI-generated and it's unfortunate the author didn't clean it up.

[−] causal 45d ago
I'm amazed at how much of what my past employers would call trade secrets are just being shipped in the source. Including comments that just plainly state the whole business backstory of certain decisions. It's like they discarded all release harnesses and project tracking and just YOLO'd everything into the codebase itself.

Edit: Everyone is responding "comments are good" and I can't tell if any of you actually read TFA or not

> “BQ 2026-03-10: 1,279 sessions had 50+ consecutive failures (up to 3,272) in a single session, wasting ~250K API calls/day globally.”

This is just revealing operational details the agent doesn't need to know to set MAX_CONSECUTIVE_AUTOCOMPACT_FAILURES = 3

[−] layer8 45d ago

> Sometimes a regex is the right tool.

I’d argue that in this case, it isn’t. Exhibit 1 (from the earlier thread): https://github.com/anthropics/claude-code/issues/22284. The user reports that this caused their account to be banned: https://news.ycombinator.com/item?id=47588970

Maybe it would be okay as a first filtering step, before doing actual sentiment analysis on the matches. That would at least eliminate obvious false positives (but of course still do nothing about false negatives).

[−] girvo 45d ago
I'd really recommend putting a modicum of work into cleaning up obvious AI generated output. It's rude, otherwise, to the humans you're expecting to read this.
[−] simianwords 45d ago

> The multi-agent coordinator mode in coordinatorMode.ts is also worth a look. The whole orchestration algorithm is a prompt, not code.

So much for langchain and langraph!! I mean if Anthropic themselves arent using it and using a prompt then what’s the big deal about langchain

[−] viccis 45d ago

>This was the most-discussed finding in the HN thread. The general reaction: an LLM company using regexes for sentiment analysis is peak irony.

>Is it ironic? Sure. Is it also probably faster and cheaper than running an LLM inference just to figure out if a user is swearing at the tool? Also yes. Sometimes a regex is the right tool.

I'm reading an LLM written write up on an LLM tool that just summarizes HN comments.

I'm so tired man, what the hell are we doing here.

[−] HeytalePazguato 45d ago
The hooks system is the most underappreciated thing in what leaked. PreToolUse, PostToolUse, session lifecycle, all firing via curl to a local server. Clean enough to build real tooling on top of without fighting it.

The frustration regex is funny but honestly the right call. Running an LLM call just to detect "wtf" would be ridiculous.

KAIROS is what actually caught my attention. An always-on background agent that acts without prompting is a completely different thing from what Claude Code is today. The 15 second blocking budget tells me they actually thought through what it feels like to have something running in the background while you work, which is usually the part nobody gets right.

[−] Levitating 45d ago
I am still just shocked that Claude Code was written in Typescript, not C++, Rust or Python.

It also somehow messed up my alacritty config when I first used it. Who knows what other ~/.config files it modifies without warning.

[−] artyom 45d ago
I'm still amazed that something as ubiquitous as "daemon mode" is still unreleased.

- Claude Chat: built like it's 1995, put business logic in the button click() handler. Switch to something else in in the UI and a long running process hard stops. Very Visual Basic shovelware.

- Claude Cowork: same but now we're smarter, if you change the current convo we don't stop the underlying long-running process. 21st century FTW!

- Claude Code: like chat, but in the CLI

- Claude Dispatch: an actual mobile client app, not the whole thing bundled together.

- Daemon mode: proper long-running background process, still unreleased.

[−] pixl97 45d ago

>Claude Code also uses Axios for HTTP.

Interesting based on the other news that is out.

[−] preston-kwei 45d ago
I’m more curious how this impacts trust than anything else.

In the span of basically a week, they accidentally leaked Mythos, and then now the entire codebase of CC. All while many people are complaining about their usage limits being consumed quickly.

Individually, each issue is manageable (Because its exciting looking through leaked code). But together, it starts to feel like a pattern.

At some point, I think the question becomes whether people are still comfortable trusting tools like this with their codebases, not just whether any single incident was a mistake.

[−] deepsun 45d ago
It is super weird that developers have to run a binary blob on their machines. It's 2026, all the major developer CLI tools are open-source anyway. What's the point for Anthropic to even make it secret?
[−] galaxyLogic 45d ago
The irony of ironies is in the last paragraph:

" ...accidentally shipping your source map to npm is the kind of mistake that sounds impossible until you remember that a significant portion of the codebase was probably written by the AI you are shipping.”

[−] Andebugulin 45d ago
Regex for swearing detected, user needs to get more API tokens, he is very very pissed.
[−] stavros 45d ago
Can someone clarify how the signing can't be spoofed (or can it)? If we have the source, can't we just use the key to now sign requests from other clients and pretend they're coming from CC itself?
[−] SquibblesRedux 45d ago
Can fully AI‑generated code be copyrightable? Is there evidence that the leaked code was AI-generated?
[−] wg0 45d ago
I have yet to see such a company that's so insecure that they would keep their CLI closed source even when the secret sauce is in the model that they control already and is closed source.

Not only that, wouldn't allow other CLIs to be used either.

[−] tylerloveamber 40d ago
The "undercover mode" discussion here is exactly the kind of thing non-technical CEOs need to understand — not the implementation, but the governance implication. If your developers are using a tool that actively avoids disclosing its involvement in commits and PRs, your audit trail is broken.

I wrote a short piece explaining the 3 policy implications for teams using Claude Code (or any AI coding tool) — without the technical jargon: https://www.aipolicydesk.com/blog/claude-code-leak-what-ceo-...

The short version: rotate API keys as a precaution, check what audit logs you actually have, and add a clause to your AI policy requiring vendor disclosure of new autonomous capabilities before they get enabled.

[−] Aperocky 45d ago
It's completely baffling to me why a client that must run on third party environment is behind closed source.
[−] seanwilson 45d ago
Anyone else have CI checks that source map files are missing from the build folder? Another trick is to grep the build folder for several function/variable names that you expect to be minified away.
[−] dangus 45d ago
Something I’ve been thinking about, somewhat related but also tangential to this topic:

The more code gets generated by AI, won’t that mean taking source code from a company becomes legal? Isn’t it true that works created with generative AI can’t be copyrighted?

I wonder if large companies have throught of this risk. Once a company’s product source code reaches a certain percentage of AI generation it no longer has copyright. Any employee with access can just take it and sell it to someone else, legally, right?

[−] simianwords 45d ago

> The obvious concern, raised repeatedly in the HN thread: this means AI-authored commits and PRs from Anthropic employees in open source projects will have no indication that an AI wrote them. It’s one thing to hide internal codenames. It’s another to have the AI actively pretend to be human.

I don’t get it. What does this mean? I can use Claude code now without anyone knowing it is Claude code.

[−] evil-olive 45d ago

> So I spent my morning reading through the HN comments and leaked source.

> This was one of the first things people noticed in the HN thread.

> The obvious concern, raised repeatedly in the HN thread

> This was the most-discussed finding in the HN thread.

> Several people in the HN thread flagged this

> Some in the HN thread downplayed the leak

when the original HN post is already at the top of the front page...why do we need a separate blogpost that just summarizes the comments?

[−] tietjens 45d ago
This is very much AI written, right? The voice sounds like Claude.
[−] martin-t 45d ago
As per https://drewdevault.com/2025/04/20/2025-04-20-Tech-sector-re... I congratulate the employee responsible.
[−] jrflowers 45d ago
I like that if they decide that your usage looks like distillation it just becomes useless, because there’s no way for the end user to distinguish between it just being sort of crappy or sabotaged intentionally. That’s a cool thing to pay for
[−] stephbook 45d ago
Sounds like there's still a lot of value in Typescript (otherwise they could have open sourced.)

Plus there's demand for skilled TS software devs that don't ship your company's roadmap using a js.map

20,000 agents and none of them caught it...

[−] marcd35 45d ago

> 250,000 wasted API calls per day

How much approximate savings would this actually be?

[−] senfiaj 45d ago

> Frustration detection via regex (yes, regex)

/\b(wtf|wth|ffs|omfg|shit(ty|tiest)?|dumbass|horrible|awful| piss(ed|ing)? off|piece of (shit|crap|junk)|what the (fuck|hell)| fucking? (broken|useless|terrible|awful|horrible)|fuck you| screw (this|you)|so frustrating|this sucks|damn it)\b/

Personally, I'm generally polite even towards AI and even when frustrated. I simply point out the its mistakes instead of using emotional words.

[−] maguay 44d ago
Absolutely hilarious that it's watching for frustration.

I'd discovered, perhaps mid-2025, that Cursor was noticeably better at fixing bugs if I started cursing at it. Better yet, after a while it would seem to break and start cursing itself ("Oh yes, I see the f*** problem now" and so on). Hilarity ensued.

What a world, where cursing at your machines can make them get their act together.

[−] karim79 45d ago
We're about to reach AGI. One regex at a time...
[−] pjoubert 45d ago
I'm curious about what people are not looking for about Claude code. What's missing and nobody is talking about? Any clue?
[−] motbus3 45d ago
I am curious about these fake tools.

They would either need to lie about consuming the tokens at one point to use in another so the token counting was precise.

But that does not make sense because if someone counted the tokens by capturing the session it would certainly not match what was charged.

Unless they would charge for the fake tools anyway so you never know they were there

[−] try-working 45d ago
They want "Made with Claude Code" on your PRs as a growth marketing strategy. They don't want it on their PRs, so it looks like they're doing something you're not capable of. Well, you are and they have no secret sauce.
[−] Gen_ArmChair 45d ago
The Claude Code leak suggests multi-agent orchestration is largely driven by prompts (e.g., “do not rubber-stamp weak work”), with code handling execution rather than enforcing decisions.

Prompts are not hard constraints—they can be interpreted, deprioritized, or reasoned around, especially as models become more capable.

From what’s visible, there’s no clear evidence of structural governance like voting systems, hard thresholds, or mandatory human escalation. That means control appears to be policy (prompts), not enforcement (code).

This raises the core issue: If governance is “prompts all the way down,” it’s not true governance—it’s guidance.

And as model capability increases, that kind of governance doesn’t get stronger—it becomes easier to bypass without structural constraints.

Has anyone actually implemented structural governance for agent swarms — voting logic, hard thresholds, REQUIRES_HUMAN as architecture not instruction?

[−] olalonde 45d ago
I'm surprised that they don't just keep the various prompts, which are arguably their "secret sauce", hidden server side. Almost like their backend and frontend engineers don't talk to each other.
[−] armanj 45d ago

> Anti-distillation: injecting fake tools to poison copycats

Does this mean huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled is unusable? Had anyone seen fake tool calls working with this model?

[−] mmaunder 45d ago
Come on guys. Yet another article distilling the HN discussion in the original post, in the same order the comments appear in that discussion? Here's another since y'all love this stuff: https://venturebeat.com/technology/claude-codes-source-code-...
[−] seertaak 45d ago
The irony of an IP scraper on an absolutely breathtaking, epic scale getting its secret sauce "scraped" - because the whole app is vibe coded (and the vibe coders appear to be oblivious to things like code obfuscation cuz move fast!)...

And so now the copy cats can ofc claim this is totally not a copy at all, it's actually Opus. No license violation, no siree!

It's fucking hilarious is what it is, it's just too much.