Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code's source code has been leaked via a map file in their NPM registry

twitter.com

Post reply on HN
Print view View original

981–990 of 1001 posts

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#981

Post by alxndr »

soiltype wrote: post #894
SoftTalker wrote: post #521

Earlier quoted context omitted.

Always seems strange to me that people say "please" and "thank you" to LLMs.

It seems strange to you? It's natural to how I write - intentionally avoiding politeness would be weirder to me. But aside from that, an LLM is only a roleplayer. Treat it like an idiot that makes mistakes and it will act like one. Treat it like a coworker who you respect and it will act like one, and it will find better results. Obviously nothing about how they act is set in stone but as a general rule this seems to…

I think if you treat it like a coworker who you respect, it will speak to you like a coworker who respects you, but will still make some idiotic mistakes...

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#982

Post by AlexCoventry »

olmo23 wrote: post #344
grey-area wrote: post #190

Earlier quoted context omitted.

LLMs are so so far away from being able to independently work on a large codebase, and why would they not benefit from modularity and clarity too?

I agree the functions in a file should probably be reasonably-sized. It's also interesting to note that due to the way round-tripping tool-calls work, splitting code up into multiple files is counter-productive. You're better off with a single large file.

> due to the way round-tripping tool-calls work, splitting code up into multiple files is counter-productive.

Can you expand on that?

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#983

Post by weird-eye-issue »

sodapopcan wrote: post #974
weird-eye-issue wrote: post #963

Earlier quoted context omitted.

No reasonable person actually thinks that Claude Code cannot make mistakes. So if your point is that this is going to change anybody's opinion about it then I think that's pretty silly. Also who really cares about the roadmap? Any feature they release can be easily copied quickly. The only moat they have at the moment is in giving access to their models via a subscription.

> No reasonable person actually thinks that Claude Code cannot make mistakes. This was insanely rookie mistake that could have been caught if anyone was paying attention as opposed to "vibing."

As a Claude Code user why should I care?

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#984

Post by grey-area »

zer00eyz wrote: post #813
grey-area wrote: post #190

Earlier quoted context omitted.

LLMs are so so far away from being able to independently work on a large codebase, and why would they not benefit from modularity and clarity too?

> independently work on a large codebase Im not sure that Humans are great at this either. Think about how we use frameworks and have complex supply chains... we sort of get "good enough" at what we need to do and pray a lot that everything else keeps working and that our tooling (things like artifactory) save us from supply chain attacks. Or we just run piles of old, outdated code because "it works". I cant tell you…

I think humans are pretty good at it with small teams and the right structure. There are definitely dysfunctional orgs as you describe where humans produce garbage code yes. I blame the org for that, not the humans.

As to what defines clarity, yes of course, like the word quality this is very hard to define, but we can certainly recognise when it was not considered.

I think it is a goal worth striving for though, and abandoning code standards because we now have AI helpers is stupid and self-defeating, even if we think they are very capable and will improve.

The end of history has not in fact arrived with generative AI, we still have to maintain software after.

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#985

Post by efskap »

withinboredom wrote: post #144
delamon wrote: post #41

Earlier quoted context omitted.

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.

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".

Wait, is it expected for them to be able to change? According to this SO answer [0] it's only really possible through GDB or "nasty hacks" as there's no API for it.

[0] https://unix.stackexchange.com/questions/38205/change-enviro...

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#986

Post by huang-b62b5756 »

cedws wrote: post #69

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…

It is a RCE, if what’s being injected is an executable and malicious tool

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#987

Post by 0x3f »

gspr wrote: post #977
0x3f wrote: post #947

Earlier quoted context omitted.

Well why not head for the front lines of Ukraine? Or Russia, depending on your preference.

This is such an incredibly imbecilic comment. Listen to this guy: "because you don't take the ultimate risk for what you believe in, you are dumb for suggesting you should do anything whatsoever". Go away. The world doesn't need your dark resignation.

Wasting your life fighting things that can't be fought is functionally equivalent to dying sooner.

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#989

Post by viktorianer »

lopsotronic wrote: post #445
BoppreH wrote: post #103

Earlier quoted context omitted.

An LLM company using regexes for sentiment analysis? That's like a truck company using horses to transport parts. Weird choice.

The difference in response time - especially versus a regex running locally - is really difficult to express to someone who hasn't made much use of LLM calls in their natural language projects. Someone said 10,000x slower, but that's off - in my experience - by about four orders of magnitude. And that's average, it gets much worse. Now personally I would have maybe made a call through a "traditional" ML widget (sciki…

[flagged]

Re: Claude Code's source code has been leaked via a map file in their NPM registry

#990

Post by snapcaster »

brookst wrote: post #548
snapcaster wrote: post #364

Earlier quoted context omitted.

No it isn't. It's a competition, making moves that benefit you and attempting to deprive your opponent of the same move is just called competing

Wait, are you saying that it's not hypocritical for my chess opponent to try to protect their king while trying to kill mine? :mind-blown: Tech people are funny, with these takes that businesses do/should adhere to absolute platonic ideals and follow them blindly regardless of context.

Yeah man I would love to play poker against these people
Post reply on HN