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

Field Notes from Shipping Real Code with Claude

diwank.space

Post reply on HN
Print view View original

81–90 of 107 posts

Re: Field Notes from Shipping Real Code with Claude

#81

Post by __mharrison__ »

tomhow wrote: post #34
diwank wrote: post #8

Earlier quoted context omitted.

I’d say around ~40% me, the ideating, editing, citations, and images are all mine; rest Opus 4 :) I typically try to also include the original Claude chat’s link in the post but it seems like Claude doesn’t allow sharing chats with deep research used in them. Update : here’s an older chatgpt conversation while preparing this: https://chatgpt.com/share/6844eaae-07d0-8001-a7f7-e532d63bf8...

Thanks for being transparent about this, but we’re not wanting substantially LLM-generated content on HN. We’ve been asking the community to refrain from publicly accusing authors of posting LLM-generated articles and comments. But the other side of that is that we expect authors to post content thay they’ve created themselves. It’s one thing to use an LLM for proof-reading and editing suggestions, but quite another…

Speaking for this "we", this was one of the best posts I read this week. (And I imagine that a lot of them were AI-assisted.)

Re: Field Notes from Shipping Real Code with Claude

#82

Post by __mharrison__ »

nxobject wrote: post #66

As I read (and appreciate) your documentation tips, I don’t even think they have to be labeled as AI-specific! ‘CLAUDE.md’ seems likely it could just as be ‘CONVENTIONS.md’, and comments to ‘AI’ could just as be comments to ‘READER’. :) Certainly I would appreciate comments like that when reading _any_ codebase, especially as an unfamiliar contributor.

I just tried this out with aider. It worked great. Vibe coded a PDF viewer with drawing capabilities in 30 minutes while waiting for a plane...

Re: Field Notes from Shipping Real Code with Claude

#83

Post by threeseed »

m_kos wrote: post #78

Good read – I have learned something new. I have been having a horrible experience with Sonnet 4 via Cursor and Web. It keeps cutting corners and misreporting what it did. These are not hallucinations. Threatening it with deletion (inspired by Anthropic's report) only makes things worse. It also pathologically lies about non-programming things. I tried reporting it but the mobile app says "Something went wrong. Pleas…

Routinely had every one of these issues.

I find it's much better just to use Claude Web and be extremely specific about what I need it to do.

And even then half the code it generates for me is riddled with errors.

Re: Field Notes from Shipping Real Code with Claude

#84

Post by threeseed »

ericb wrote: post #67
tomhow wrote: post #34

Earlier quoted context omitted.

Thanks for being transparent about this, but we’re not wanting substantially LLM-generated content on HN. We’ve been asking the community to refrain from publicly accusing authors of posting LLM-generated articles and comments. But the other side of that is that we expect authors to post content thay they’ve created themselves. It’s one thing to use an LLM for proof-reading and editing suggestions, but quite another…

Is the percentage meaningful, though? If an LLM produces the most interesting, insightful, thought-provoking content of the day, isn't that what the best version of HN would be reading and commenting on? If I invent the wheel, and have an LLM write 90% of the article from bullet points and edit it down, don't we still want HN discussing the wheel? Not to say that the current generation of AI isn't often producing bor…

> If an LLM produces the most interesting, insightful, thought-provoking content of the day, isn't that what the best version of HN would be reading and commenting on?

Absolutely not. Would much rather take some that is boring, not thought provoking but that was authentic and real rather than as you say AI slop.

If you want that sort of content maybe LinkedIn is a better place.

Re: Field Notes from Shipping Real Code with Claude

#85

Post by j_crick »

m_kos wrote: post #78

Good read – I have learned something new. I have been having a horrible experience with Sonnet 4 via Cursor and Web. It keeps cutting corners and misreporting what it did. These are not hallucinations. Threatening it with deletion (inspired by Anthropic's report) only makes things worse. It also pathologically lies about non-programming things. I tried reporting it but the mobile app says "Something went wrong. Pleas…

I think they might have cut its brains too much in the latest updates.

I remember versions 3.5 doing okay on my simple tasks like text analysis or summaries or little writing prompts. In 4+ versions the thing just can't follow instructions within a single context window for more than 3-4 replies.

When prompted about "why do you keep rambling if I asked you to stay concise" it says that its default settings are overriding its behavior and explicit user instructions, ditto for actively avoiding information that it considers "harmful". After pointing out inconsistencies and omissions in its replies it concedes that its behavior is unreliable and even extrapolates that it is made this way so users keep engaging with it for longer and more often.

Maybe it got too smart to its detriment, but if yes then it's really sad what Anthropic did to it.

Re: Field Notes from Shipping Real Code with Claude

#87

Post by wredcoll »

m_kos wrote: post #78

Good read – I have learned something new. I have been having a horrible experience with Sonnet 4 via Cursor and Web. It keeps cutting corners and misreporting what it did. These are not hallucinations. Threatening it with deletion (inspired by Anthropic's report) only makes things worse. It also pathologically lies about non-programming things. I tried reporting it but the mobile app says "Something went wrong. Pleas…

What's the difference between "sonnet 4 via cursor" and claude code?

Re: Field Notes from Shipping Real Code with Claude

#88

Post by wredcoll »

diwank wrote: post #61
skerit wrote: post #44

Very interesting, I'm going to use some of these ideas in my CLAUDE.md file. > One of the most counterintuitive lessons in AI-assisted development is that being stingy with context to save tokens actually costs you more Something similar I've been thinking about recently: For bigger projects & more complicated code, I really do notice a big difference between Claude Opus and Claude Sonnet. And Sonnet sometimes just w…

yeah, the max subscription comes in two tiers, $100 gets you 5x the tokens than pro (which only has sonent) and the $200 gets you 20x. doing the math for tokens is kinda annoying and not straightforward atm. they also have a "hybrid" mode which uses opus until ~20% tokens for opus left then switches to sonnet

How do you get opus on a subscription? Their system is so confusing.

Re: Field Notes from Shipping Real Code with Claude

#90

Post by linsomniac »

wredcoll wrote: post #87
m_kos wrote: post #78

Good read – I have learned something new. I have been having a horrible experience with Sonnet 4 via Cursor and Web. It keeps cutting corners and misreporting what it did. These are not hallucinations. Threatening it with deletion (inspired by Anthropic's report) only makes things worse. It also pathologically lies about non-programming things. I tried reporting it but the mobile app says "Something went wrong. Pleas…

What's the difference between "sonnet 4 via cursor" and claude code?

"Sonnet 4" is the model, "cursor" is the IDE. "Claude Code" is another IDE, a TUI with a chat interface. Cursor is a VSCode fork with an AI panel in it.
Post reply on HN