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

71–80 of 107 posts

Re: Field Notes from Shipping Real Code with Claude

#71

Post by thelittleone »

StefanBatory wrote: post #41
Artoooooor wrote: post #16

I finally decided few days ago to try this Claude Code thing in my personal project. It's depressingly efficient. And damn expensive - I used over 10 dollars in one day. But I'm afraid it is inevitable - I will have to pay tax to AI overlords just to be able to keep my job.

I had been musing over this. Will devs in very cheap countries still stay an attractive option, just because they'd be still cheaper monthly than Claude.

The cost on paper may be cheaper. But those options become less attractive when you take into account timezones, communication challenges, availability, scheduling, and the ever increasing coding performance of coding agents.

Re: Field Notes from Shipping Real Code with Claude

#72

Post by SatvikBeri »

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.

Not the OP, but in practice, the comments that tend to help Claude tend to be very different from what helps humans. With humans, I'll generally focus on the why.

Our style guide for humans is about 100 lines long, with lines like "Add a ! to the end of a function name if and only if it mutates one of its inputs". Our style guide for Claude is ~500 lines long, and equivalent sections have to include many examples like "do this, don't do this" to work.

Re: Field Notes from Shipping Real Code with Claude

#73

Post by diwank »

r0b0ji wrote: post #68
diwank wrote: post #5

Author here: To be honest, I know there are like a bajillion Claude code posts out there these days. But, there are a few nuggets we figured are worth sharing, like Anchor Comments [1], which have really made a difference: —— # CLAUDE.md ### Anchor comments Add specially formatted comments throughout the codebase, where appropriate, for yourself as inline knowledge that can be easily `grep`ped for. - Use `AIDEV-NOTE:…

At one place you mentioned, if a test is updated by AI, you reject the PR. How do you know if it was generated or updated by AI. From the article I only got that it's a git commit message convention to add that but that too is only at commit level.

Mostly just good faith during PR reviews. Plus other than Opus 4 models largely flub it and it shows

Re: Field Notes from Shipping Real Code with Claude

#74

Post by mgraczyk »

Good post, the only part I think I disagree with is

> Never. Let. AI. Write. Your. Tests.

AI writes all of my tests now, but I review them all carefully. Especially for new code, you have to let the AI write tests if you want it to work autonomously. I explicitly instruct the AI to write tests and make sure they pass before stopping. I usually review these tests while the AI is implementing the code to make sure they make sense and cover important cases. I add more cases if they are inadequate.

Re: Field Notes from Shipping Real Code with Claude

#75

Post by never_inline »

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…

Because why do you anti-compress your thoughts using LLM at all? It makes things harder to read.

Re: Field Notes from Shipping Real Code with Claude

#76

Post by noufalibrahim »

diwank wrote: post #5

Author here: To be honest, I know there are like a bajillion Claude code posts out there these days. But, there are a few nuggets we figured are worth sharing, like Anchor Comments [1], which have really made a difference: —— # CLAUDE.md ### Anchor comments Add specially formatted comments throughout the codebase, where appropriate, for yourself as inline knowledge that can be easily `grep`ped for. - Use `AIDEV-NOTE:…

There are a lot of posts around but this was very practical and gives me a system i can try to implement and perhaps improve. Much appreciated. Thanks for taking the time to write it.

One thing I would have liked to know is the difference between a workflow like this and the use of aider. If you have any perspective on that, it would be great.

Re: Field Notes from Shipping Real Code with Claude

#77

Post by misnome »

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…

Wasn’t it “40% me” e.g. 60% LLM generated?

“I supplied the ideas” is literally the first thing anyone caught out using chatgpt to do their homework says… I’d tend to believe someones first statement instead of the backpedal once they’ve been chastised for it.

Re: Field Notes from Shipping Real Code with Claude

#78

Post by m_kos »

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. Please try again later." Very bizarre.

Am I the only person experiencing these issues? Many here seem to adore Claude.

Re: Field Notes from Shipping Real Code with Claude

#80

Post by panny »

diwank wrote: post #5

Author here: To be honest, I know there are like a bajillion Claude code posts out there these days. But, there are a few nuggets we figured are worth sharing, like Anchor Comments [1], which have really made a difference: —— # CLAUDE.md ### Anchor comments Add specially formatted comments throughout the codebase, where appropriate, for yourself as inline knowledge that can be easily `grep`ped for. - Use `AIDEV-NOTE:…

>Think of this post as your field guide to a new way of building software. By the time you finish reading, you’ll understand not just the how but the why behind AI-assisted development that actually works.

Hi, AI skeptic with an open-mind here. How much will this cost me to try? I don't see that mentioned in your writeup.

Post reply on HN