Live data from Hacker News

The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

alex000kim.com

511–520 of 636 posts

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#511

Earlier quoted context omitted.

Anthropic acquired Bun. Clearly, Bun is not a runtime for C++, Rust, or Python. For an engineering project, strongly typed TypeScript was basically the only possible choice for them.

I am not following your logic. Anthropic acquired Bun and so all of their end-user software should use it? Or am I missing sarcasm?

Why do you think they acquired Bun. To look at it?

Also you needed a leak to know that CC, that is out for 1 year, is in TS?

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#512

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.

Boris Cherney is author of a oreilly book about typescript

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#513

Earlier quoted context omitted.

Why? What does this have to do with the leak

...Because it's a mode of using Claude Code that allows certain users to use the application in "stealth mode" to produce pull requests that seem human, but are actually AI generated, which often goes against the contribution rules of OSS projects? At this point I would consider any employee of an AI provider to be tainted.

None of the other agents claim that the commit was made by an AI so why the panic suddenly

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#514
post #81

>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.…

[dead]

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#515
post #511

Earlier quoted context omitted.

I am not following your logic. Anthropic acquired Bun and so all of their end-user software should use it? Or am I missing sarcasm?

Why do you think they acquired Bun. To look at it? Also you needed a leak to know that CC, that is out for 1 year, is in TS?

> Why do you think they acquired Bun

I don't know why they acquired Bun. Surely not because there's no other means to write command line programs.

> Also you needed a leak to know that CC, that is out for 1 year, is in TS?

What, are you shaming people for not being aware what (obfuscated) code some 1 year old software is written in?

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#516

Earlier quoted context omitted.

> If you're not using comments, you're doing agent coding wrong. Comments are ultimately so you can understand stuff without having to read all the code. LLMs are great when you force them to read all code, and comments only serve to confuse. I'd say the opposite been true in my experience, if you're not forcing LLMs to not have any comments at all (and it can actually skip those, looking at you Gemini), you're doing…

You're wasting context doing that when a 3 line comment that the agent itself leaves can prevent the agent from searching and reading 30 files.

You're wasting context re-specifying what the code should already say, defining an implementation once should be enough, otherwise try another model that can correctly handle programming.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#517

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.

Anthropic acquired Bun. Clearly, Bun is not a runtime for C++, Rust, or Python. For an engineering project, strongly typed TypeScript was basically the only possible choice for them.

Anthropic acquired Bun after making Claude Code.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#518
post #376

Earlier quoted context omitted.

Poor babies. Again, I don’t care about them.

it's not about the companies, what a myopic viewpoint every delay to AGI results in deaths that AGI could have prevented. we are talking millions of deaths for, say, just a year's delay.

I thought we gave up on AGI and turned into making sex chatbots and simulated porn instead. Wasn't that what Sam was pushing for all along when he went all in on Sora and the erotic modes?

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#519

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.

I'm surprised Python is on that list. TypeScript doesn't seem like a terrible choice, as it can leverage vast ecosystems of packages, has concurrency features, a solid type system, and decent performance. C++ lacks as robust of a package ecosystem, and Python doesn't have inbuilt types, which makes it a non-starter for larger projects for me. Rust would have been a great choice for sure.

>Python doesn't have inbuilt types

Technically, neither does JavaScript.

Post reply on HN