961–970 of 1001 posts
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...
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
It's definitely still hypocrisy.
Earlier quoted context omitted.
It doesn't matter that much. Trust me you could just have an LLM reverse engineer the obfuscated code.
The point is that a "secure coding platform" leaked something they were trying to keep under wraps, whether the contents of the leak matter or not. Also, as many others have pointed out, there is roadmap info in here that wouldn't be available in the production build.
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.
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…
I wonder it CC thinks I'm trying to distill the model. This is a common enough use case that I think the devs at Anthropic should consider.
Earlier quoted context omitted.
what does that even do?
Looks like it tries wl-copy, then tries xclip and then tries xsel. I have no idea what those are but google says it's for Wayland, so, I think it's a linux function trying to copy to clipboard? I think their problem is with the use of '.then(...=>...)' since there doesn't seem to be a way to tell each function that the nested ones actually finished.
xclip is the same for X based systems.
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 - Un…
src/cli/print.ts 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, wo…
How is it that a AI coding agent that is supposedly _so great at coding_ is running on this kind of slop behind the scenes. /s
Earlier quoted context omitted.
(I mostly agree with you, but) devils advocate: most people already do that with dependencies, so why not move the line even further up?
Because you trust that your dependencies are not vibe coded and have been reviewed by humans.