591–600 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...
An LLM company using regexes for sentiment analysis? That's like a truck company using horses to transport parts. Weird choice.
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
I've checked, current Claude Code 2.1.87 uses Axios version is 1.14.0, just one before the compromised 1.14.1 To stop Claude Code from auto-updating, add `export DISABLE_AUTOUPDATER=1` to your global environment variables (~/.bashrc, ~/.zshrc, or such), restart all sessions and check that it works with `claude doctor`, it should show `Auto-updates: disabled (DISABLE_AUTOUPDATER set)`
Earlier quoted context omitted.
Ye I honestly don't understand his comment. Is it bad code writing? Pre 2026? Sure. In 2026. Nope. Is it going to be a headache for some poor person on oncall? Yes. But then again are you "supposed" to go through every single line in 2026? Again no. I hate it. But the world is changing and till the bubble pops this is the new norm
Sorry, I was not clear enough. My first word was litteraly "Yes", so I agree that a function like this is a maintenance nightmare for a human. And, sure, the code might not be "optimized" for the LLM, or token efficiency. However, to try and make my point clearer: it's been reported that anthropic has "some developpers won't don't write code" [1]. I have no inside knowledge, but it's possible, by extension, to assume…
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…
the claude code team ethos, as far as i’ve been lead to understand— which i agree with, mind you— is that there is no point in code-reviewing ai-generated code… simply update your spec(s) and regenerate. it is just a completely different way of interacting with the world. but it clearly works for them, so people throwing up their hands should at least take notice of the fact that they are absolutely not competing wit…
Earlier quoted context omitted.
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…
They're sending it to an llm anyway tho? Not sure why they wouldn't just add a sentiment field to the requested response shape.
Earlier quoted context omitted.
It's how people resisted CGI back in the day. What people dislike is low quality. There is a loud subset who are really against it on principle like we also have people who insist on analog music but regular people are much more practical but they don't post about this all day on the internet.
I think literally everyone could agree CGI has been detrimental to the quality of films.
Same thing is true of AI output.
Earlier quoted context omitted.
> I don't like reading leaked code Don't worry about that, the code in that repository isn't Anthropic's to begin with.
You believe it's just a fake ? (That would be ironic if the fake was generated by... claude itself. Anyway.)
Earlier quoted context omitted.
So, think of it as a business man: You don't really care if your customers swear or whatever, but you know that it'll generate bad headlines. So you gotta do something. Just like a door lock isn't designed for a master criminal, you don't need to design your filter for some master swearer; no, you design it good enough that it gives the impression that further tries are futile. So yeah, you do what's less intesive to…
This door lock doesn’t even work against people speaking French, so I think they could have tried a mite harder.