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

181–190 of 491 posts

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

#181

Post by blitz_skull »

hansmayer wrote: post #177
blitz_skull wrote: post #172

Earlier quoted context omitted.

This seems pretty aggressive considering this is all just personal anecdote. I update my CLAUDE.md all the time and notice the effects. Why all the snark?

Is it really just a personal anecdote ? Please do read some other comments on this post. The snark comes from everyone and their mother recommending "just write CLAUDE.md", when it is clear that this technology does not have intrinsic capability to perform reliable outputs based on human language input.

Yeah… that’s the point of LLMs: variable output. If you’re using them for 100% consistent output, you’re using the wrong tool.

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

#182

Post by hansmayer »

MontyCarloHall wrote: post #169
matt3210 wrote: post #111

Earlier quoted context omitted.

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

Good question. Why hasn't there been a profusion of new game-changing software, fixes to long-standing issues in open-source software, any nontrivial shipped product at all? Heck, why isn't there a cornucopia of new apps, even trivial ones? Where is all the shovelware [0]? Previous HN discussion here [1]. Don't get me wrong, AI is at least as game-changing for programming as StackOverflow and Google were back in the…

Well, the LLM industry is not completely without results. We do have ever increasing frequency of outages in major Internet services...Somehow correlates with the AI mandates major tech corps seem to pushing now internally.

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

#183

Post by hansmayer »

blitz_skull wrote: post #181
hansmayer wrote: post #177

Earlier quoted context omitted.

Is it really just a personal anecdote ? Please do read some other comments on this post. The snark comes from everyone and their mother recommending "just write CLAUDE.md", when it is clear that this technology does not have intrinsic capability to perform reliable outputs based on human language input.

Yeah… that’s the point of LLMs: variable output. If you’re using them for 100% consistent output, you’re using the wrong tool.

Is it? So you are saying software should not be consistent? Or that LLMs should not be used for software development, aside from toy-projects?

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

#184

Post by danenania »

Kubuxu wrote: post #171
shsush wrote: post #160

Earlier quoted context omitted.

The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing. Very pro agent devs like ghuntley will all say this. And it makes sense. For most coding problems the challenge isn’t writing code. Once you know what to write typing the code is a drop in the bucket. AI is still very useful, but if you really wanna go fast you have to give up on you…

I don’t see how I would feel comfortable pushing the current output of LLMs into high-stakes production (think SLAs, SRE). Understanding of the code in these situation is more important than the code/feature existing.

You can use an agent while still understanding the code it generates in detail. In high stakes areas, I go through it line by line and symbol by symbol. And I rarely accept the first attempt. It’s not very different from continually refining your own code until it meets the bar for robustness.

Agents make mistakes which need to be corrected, but they also point out edge cases you haven’t thought of.

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

#185

Post by glamp »

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…

Hey Boris,

I couldn't agree more. And using Plan mode was a major breakthrough for me. Speaking of Plan Mode...

I was previously using it repeatedly in sessions (and was getting great results). The most recent major release introduced this bug where it keeps referring back to the first plan you made in a session even when you're planning something else (https://github.com/anthropics/claude-code/issues/12505).

I find this bug incredibly confusing. Am I using Plan Mode in a really strange way? Because for me this is a showstopper bug–my core workflow is broken. I assume I'm using Claude Code abnormally otherwise this bug would be a bigger issue.

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

#186

Post by submain »

shsush wrote: post #160
matt3210 wrote: post #126

Earlier quoted context omitted.

Can you show some example? I feel like there would be streams or YouTube lets plays on this if it was working well

The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing. Very pro agent devs like ghuntley will all say this. And it makes sense. For most coding problems the challenge isn’t writing code. Once you know what to write typing the code is a drop in the bucket. AI is still very useful, but if you really wanna go fast you have to give up on you…

> The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing

The few times I've done that, the agent eventually faced a problem/bug it couldn't solve and I had to go and read the entire codebase myself.

Then, found several subtle bugs (like writing private keys to disk even when that was an explicit instruction not to). Eventually ended up refactoring most of it.

It does have value on coming up with boilerplate code that I then tweak.

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

#187

Post by abdullahkhalids »

binocarlos wrote: post #26
listic wrote: post #14

Earlier quoted context omitted.

Thanks for the advice! Could you please share how did you enable voice transcription for your setup and what it actually is?

I use https://github.com/braden-w/whispering with an OpenAI api key. I use a keyboard shortcut to start and stop recording and it will put the transcription into the clipboard so I can paste into any app. It's a huge productivity boost - OP is correct about not overthinking trying to be that coherent - the models are very good at knowing what you mean (Opus 4.5 with Claude Code in my case)

I just installed this app and it is very nice. The UX is very clean and whatever I say it transcribes it correctly. In fact I'm transcribing this comment with this app just now.

I am using Whisper Medium. The only problem I see is that at the end of the message it sometimes puts a bye or a thank you which is kind of annoying.

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

#188

Post by shsush »

Kubuxu wrote: post #171
shsush wrote: post #160

Earlier quoted context omitted.

The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing. Very pro agent devs like ghuntley will all say this. And it makes sense. For most coding problems the challenge isn’t writing code. Once you know what to write typing the code is a drop in the bucket. AI is still very useful, but if you really wanna go fast you have to give up on you…

I don’t see how I would feel comfortable pushing the current output of LLMs into high-stakes production (think SLAs, SRE). Understanding of the code in these situation is more important than the code/feature existing.

I agree and am the same. Using them to enhance my knowledge and as well as autocomplete on steroids is the sweet spot. Much easier to review code if im “writing” it line by line.

I think the reality is a lot of code out there doesn’t need to be good, so many people benefit from agents etc.

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

#189

Post by spreiti »

hansmayer wrote: post #179
spreiti wrote: post #176

Earlier quoted context omitted.

I use GitHub Copilot in Intellij with Claude Sonnet and the plan mode to implement complete features without me having to code anything. I see it as a competent software developer but one that doesn't know the code base. I will break down the tasks to the same size as if I was implementing it. But instead of doing it myself, I roughly describe the task on a technical level (and add relevant classes to the context) an…

Yeah, but what did you produce with it in the end? Show us the end result please.

I cannot show it because the code belongs to my employer.

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

#190

Post by hansmayer »

matt3210 wrote: post #126
danenania wrote: post #122

Earlier quoted context omitted.

I know of many experienced and capable engineers working on complex stuff who are driving basically all their development through agents. This includes production level work. This is the norm now in the SV startup world at least. You don't just YOLO it. You do extensive planning when features are complex, and you review output carefully. The thing is, if the agent isn't getting it to the point where you feel like you…

Can you show some example? I feel like there would be streams or YouTube lets plays on this if it was working well

+1 here. Lets see those productivity gains!
Post reply on HN