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

Ask HN: How can I get better at using AI for programming?

news.ycombinator.com

Post reply on HN
Print view View original

111–120 of 491 posts

Re: Ask HN: How can I get better at using AI for programming?

#111

Post by matt3210 »

bcherny wrote: post #37

Hey, Boris from the Claude Code team here. A few tips: 1. If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself. I add to my team’s CLAUDE.md multiple times a week. 2. Use Plan mode (press shift-tab 2x). Go back and forth with Claude until you like the plan b…

I’ve yet to see any real work get done with agents. Can you share examples or videos of real production level work getting done? Maybe in a tutorial format?

My current understanding is that it’s for demos and toy projects

Re: Ask HN: How can I get better at using AI for programming?

#112

Post by newsoftheday »

Bjartr wrote: post #70
thfuran wrote: post #61

Earlier quoted context omitted.

But that documentation shouldn’t need to be updated nearly every other day.

Consider that every time you start a session with Claude Code. It's effectively a new engineer. The system doesn't learn like a real person does, so for it to improve over time you need to manually record the insights that for a normal human would be integrated by the natural learning process.

Reminds me of that Nicole Kidman movie Before I Go to Sleep.

Re: Ask HN: How can I get better at using AI for programming?

#113

Post by dyauspitr »

dominotw wrote: post #40
bogtog wrote: post #10

Using voice transcription is nice for fully expressing what you want, so the model doesn't need to make guesses. I'm often voicing 500-word prompts. If you talk in a winding way that looks awkward when in text, that's fine. The model will almost certainly be able to tell what you mean. Using voice-to-text is my biggest suggestion for people who want to use AI for programming (I'm not a particularly slow typer. I can…

surprised ai companies are not making this workflow possible instead of leaving it upto users to figure out how to get voice text into prompt.

All the mobile apps make this very easy.

Re: Ask HN: How can I get better at using AI for programming?

#114

Post by siscia »

I will be crucified by this, but I think you are doing it wrong.

I would split it in 2 steps.

First, just move it to svelte, maintain the same functionality and ideally wrap it into some tests. As mentioned you want something that can be used as pass/no-pass filter. As in yes, the code did not change the functionality.

Then, apply another pass from Svelte bad quality to Svelte good quality. Here the trick is that "good quality" is quite different and subjective. I found the models not quite able to grasp what "good quality" means in a codebase.

For the second pass, ideally you would feed an example of good modules in your codebase to follow and a description of what you think it is important.

Re: Ask HN: How can I get better at using AI for programming?

#115

Post by christophilus »

red2awn wrote: post #66
Fire-Dragon-DoL wrote: post #58

I find all AI code to be lower quality than humans who care about quality. This might be ok, I think the assumpt with AI is that we don't need to look at code so that it looks beautiful because AI will look at it .

Opus 4.5 is the highest quality code I've seen out of LLMs, still some way to go to match programmers who care, but much better than most people. I find it enough to let it write the code and then manually polish it afterwards.

Same. It is finally almost always more productive for me to use vs doing it myself. What this means for my career and life, I don’t know. But, I do think the job for most of us is going to look very different moving forward.

Re: Ask HN: How can I get better at using AI for programming?

#116

Post by dmd »

bcherny wrote: post #37

Hey, Boris from the Claude Code team here. A few tips: 1. If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself. I add to my team’s CLAUDE.md multiple times a week. 2. Use Plan mode (press shift-tab 2x). Go back and forth with Claude until you like the plan b…

I would LOVE to use Opus 4.5, but it means I (a merely Pro peon) can work for maybe 30 minutes a day, instead of 60-90.

Re: Ask HN: How can I get better at using AI for programming?

#117

Post by epolanski »

bcherny wrote: post #37

Hey, Boris from the Claude Code team here. A few tips: 1. If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself. I add to my team’s CLAUDE.md multiple times a week. 2. Use Plan mode (press shift-tab 2x). Go back and forth with Claude until you like the plan b…

> If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself.

Sure, for 4/5 interactions then will ignore those completely :)

Try for yourself: add to CLAUDE.md an instruction to always refer to you as Mr. bcherny and it will stop very soon. Coincidentally at that point also loses tracks of all the other instructions.

Re: Ask HN: How can I get better at using AI for programming?

#118

Post by matt3210 »

bcherny wrote: post #37

Hey, Boris from the Claude Code team here. A few tips: 1. If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself. I add to my team’s CLAUDE.md multiple times a week. 2. Use Plan mode (press shift-tab 2x). Go back and forth with Claude until you like the plan b…

Does all my code get uploaded to the service?

Re: Ask HN: How can I get better at using AI for programming?

#119

Post by bgilly »

bcherny wrote: post #44
dotancohen wrote: post #43

Earlier quoted context omitted.

> I add to my team’s CLAUDE.md multiple times a week. How big is that file now? How big is too big?

Try to keep it under 1k tokens or so. We will show you a warning if it might be too big. Ours is maybe half that size. We remove from it with every model release since smarter models need less hand-holding. You can also break up your CLAUDE.md into smaller files, link CLAUDE.mds, or lazy load them only when Claude works in nested dirs. https://code.claude.com/docs/en/memory

I’ve been fine tuning mine pretty often. Do you have any Claude.md files you can share as good examples? Especially with opus 4.5.

And thank you for your work!! I focus all of my energy on helping families stay safe online, I make educational content and educational products (including software). Claude Code has helped me amplify my efforts and I’m able to help many more families and children as a result. The downstream effects of your work on Claude Code are awesome! I’ve been in IT since 1995 and your tools are the most powerful tools I’ve ever used, by far.

Re: Ask HN: How can I get better at using AI for programming?

#120

Post by minimaxir »

nrds wrote: post #79
bcherny wrote: post #37

Hey, Boris from the Claude Code team here. A few tips: 1. If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself. I add to my team’s CLAUDE.md multiple times a week. 2. Use Plan mode (press shift-tab 2x). Go back and forth with Claude until you like the plan b…

> Use Opus 4.5. This drives up price faster than quality though. Also increases latency.

There's a counterintuitive pricing aspect of Opus-sized LLMs in that they're so much smarter that in some cases, it can solve the problem faster and with much fewer tokens that it can end up being cheaper.
Post reply on HN