Field Notes from Shipping Real Code with Claude • Hacker News Board

Re: Field Notes from Shipping Real Code with Claude

#91

Post by diwank » Mon, Jun 09, 2025, 3:44 AM UTC

wredcoll wrote: post #88

diwank wrote: post #61

Earlier quoted context omitted.

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.

Yeah absolutely. I’m on their Max sub since last month and I still don’t fully get how many tokens I have etc.

Simplest I’d say is: get the $100/mo Max and then npm install -g @anthropic-ai/claude-code

Re: Field Notes from Shipping Real Code with Claude

#92

Post by diwank » Mon, Jun 09, 2025, 3:46 AM UTC

mgraczyk wrote: post #74

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…

The risk, in my experience, is to reach a state where you as the dev is not easily able to understand/update the tests. That becomes very tricky

Re: Field Notes from Shipping Real Code with Claude

#93

Post by diwank » Mon, Jun 09, 2025, 3:49 AM UTC

__mharrison__ wrote: post #79

Thanks for the post. It's very interesting time navigating the nascent field of AI assisted development. Curious if the author (or others) tried other tools / models.

Have tried everything under the sun at the moment— broadly just two winners (and both have become my daily drivers for different use cases):

1. Claude Code with Opus 4

2. Cursor with Opus 4 or Gemini 2.5 Pro (Windsurf used to be an option but Anthropic has now cut them out)

3. (Coming up; still playing around) Claude Code’s GitHub Action

Re: Field Notes from Shipping Real Code with Claude

#94

Post by diwank » Mon, Jun 09, 2025, 3:59 AM UTC

noufalibrahim wrote: post #76

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.

Thank you! aider is a different beast actually, I found its memory/context handling best in class. Somehow though, I ended up liking Claude Code the most because of its TUI but really a matter of personal preference and workflow

Re: Field Notes from Shipping Real Code with Claude

#95

Post by diwank » Mon, Jun 09, 2025, 4:01 AM UTC

panny wrote: post #80

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.

There are a bunch of different options so it depends on the models you end up liking but the simplest place to start is to get Claude Max $100 tier and use Opus 4 (the others don’t really get you the full experience)

Re: Field Notes from Shipping Real Code with Claude

#96

Post by diwank » Mon, Jun 09, 2025, 4:02 AM UTC

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…

Claude Code is a really very different experience. I’d say give it a shot but Opus 4 is a step change

Re: Field Notes from Shipping Real Code with Claude

#97

Post by mcv » Mon, Jun 09, 2025, 7:19 AM UTC

diwank wrote: post #95

panny wrote: post #80

Earlier quoted context omitted.

>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.

There are a bunch of different options so it depends on the models you end up liking but the simplest place to start is to get Claude Max $100 tier and use Opus 4 (the others don’t really get you the full experience)

I hear a lot of good stuff about Claude Code lately, but before, it was all about Copilot or Cursor. And some options are a lot cheaper than others. Is Claude Code so much better now?

I admit I have no idea what the real differences are. Everybody seems to claim to be the best and most comprehensive AI coding solution.

Re: Field Notes from Shipping Real Code with Claude

#98

Post by mcv » Mon, Jun 09, 2025, 7:21 AM UTC

diwank wrote: post #73

r0b0ji wrote: post #68

Earlier quoted context omitted.

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

Really? I was hoping to use AI to write mocks. That's always the part that I hate most about unit tests.

Re: Field Notes from Shipping Real Code with Claude

#99

Post by gavinray » Mon, Jun 09, 2025, 12:34 PM UTC

localhost wrote: post #52

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:…

Did you use Claude Code to write the post? I'm finding that I'm using it for 100% of my own writing because agentic editing of markdown files is so good (and miles better than what you get with claude.ai artifacts or chatgpt.com canvas). This is how you can do things like merge deep research or other files into the doc that you are writing.

Does Claude Code perform any different than browser Claude for writing tasks?

I recently wrote a long Markdown document, and asked Claude, ChatGPT, Grok, and Gemini to improve it.

Comparing outputs, it was very close between Gemini and Claude, but I decided that Claude was slightly better-written.

Re: Field Notes from Shipping Real Code with Claude

#100

Post by localhost » Mon, Jun 09, 2025, 2:06 PM UTC

gavinray wrote: post #99

localhost wrote: post #52

Earlier quoted context omitted.

Did you use Claude Code to write the post? I'm finding that I'm using it for 100% of my own writing because agentic editing of markdown files is so good (and miles better than what you get with claude.ai artifacts or chatgpt.com canvas). This is how you can do things like merge deep research or other files into the doc that you are writing.

Does Claude Code perform any different than browser Claude for writing tasks? I recently wrote a long Markdown document, and asked Claude, ChatGPT, Grok, and Gemini to improve it. Comparing outputs, it was very close between Gemini and Claude, but I decided that Claude was slightly better-written.

The models are the same, but the actual prompts sent to the model are likely somewhat different because of the agentic loop - so I would imagine (without having done the experiments) there will be slight differences. Unclear whether they will be more or less than the variance in responses sent multiple times to the same experience (e.g., Claude.ai variance vs. Claude Code variance vs. variance between Claude.ai and Claude Code). Would be an interesting controlled experiment to try!