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

341–350 of 491 posts

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

#341

Post by simonw »

hansmayer wrote: post #338
simonw wrote: post #247

Earlier quoted context omitted.

Yes, you have to learn those things. LLMs are hard to use. So are animals, but we've used dogs and falcons and truffle hunting pigs as tools for thousands of years. Non-deterministic tools are still tools, they just take a bunch more work to figure out.

No, please, stop misleading people Simon. People use tools to make things easier for them, not harder. And a tool which I cannot steer predictably is not a god damn tool at all! The sheer persistence the AI-promoters like you are willing to invest just to gaslight us all into thinking we were dumb and did not know how to use the shit-generators is really baffling. Understand that a lot of us are early adopters and we…

Your insistence that LLMs are not useful tools is difficult for me to empathize with as someone who has been using them successfully as useful tools for several years - and sharing in great detail how I am using them.

https://simonwillison.net/2025/Dec/10/html-tools/ is the 37th post in my series about this: https://simonwillison.net/series/using-llms/

https://simonwillison.net/2025/Mar/11/using-llms-for-code/ is probably still my most useful of those.

I know you absolutely hate being told you're holding them wrong... but you're holding them wrong.

They're not nearly as unpredictable as you appear to think they are.

One of us is misleading people here, and I don't think it's me.

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

#342

Post by bonniesimon »

rgbrgb wrote: post #57
johnfn wrote: post #15

Earlier quoted context omitted.

That's a fun idea. How do you get the transcript into Claude Code (or whatever you use)? What transcription service do you use?

I use Handy with Claude code. Nice to just have a key combo to transcribe into whatever has focus. https://github.com/cjpais/Handy

Love handy. I use it too when dealing with LLMs. The other day I asked chatgpt to generate interview questions based on job description and then I answered using handy. So cool!

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

#343

Post by scellus »

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…

In other words, permanent instructions and context well presented in *.md, planning and review before execution, agentic loops with feedback, and a good model.

You can do this with any agentic harness, just plain prompting and "LLM management skills". I don't have Claude Code at work, but all this applies to Codex and GH Copilot agents as well.

And agreed, Opus 4.5 is next level.

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

#344

Post by scellus »

moribvndvs wrote: post #76
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…

Do you recommend having Claude dump your final plan into a document and having it execute from that piece by piece? I feel like when I do plan mode (for CC and competing products), it seems good, but when I tell it to execute the output is not what we planned. I feel like I get slightly better results executing from a document in chunks (which of course necessitates building the iterative chunks into the plan).

Opus 4.5 seems to be able to plan without asking, but I have used this pattern of "write a plan to an .md", review and maybe edit, and then execution, maybe in another thread,... I have used it with Codex and it works well.

Profilerating .md files need some attention though.

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

#345

Post by BoiledCabbage »

potatoman22 wrote: post #340
lkjdsklf wrote: post #330

Earlier quoted context omitted.

This is the only approach that seems even remotely reasonable “Prompt engineering” just seems dumb as hell. It’s literally just an imprecise nondeterministic programming language. Before a couple years so, we all would have said that was a bad language and moved on.

It's technically deterministic, but it feels nondeterministic in chatbots since tokens are randomly sampled (temp > 0) and input is varied. Using the right prompt makes the model perform better on average, so it's not completely dumb. I like task vectors and soft prompts because I think they show how prompt engineering is cool and useful. https://arxiv.org/pdf/2310.15916 https://huggingface.co/docs/peft/conceptual_gu…

> It's technically deterministic, but it feels nondeterministic in chatbots since tokens are randomly sampled

Are you not aware the random sampling makes something non-deterministic?

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

#347

Post by BoorishBears »

jakelazaroff wrote: post #334
BoorishBears wrote: post #332

Earlier quoted context omitted.

A few years ago we didn't have an imprecise nondeterministic programming language that would allow your mom to achieve SOTA results on a wide range of NLP tasks by asking nicely, or I'm sure people would have taken it. I think a lot of prompt engineering is voodoo, but it's not all baseless: a more formal way to look at it is aligning your task with the pre-training and post-training of the model. The whole "it's a b…

Do you mean, like, scripting languages? Are the underlying primitives C and machine language? "Might as well be well worded prompts" is the overstatement of the century; any given scripting language is far closer to those underlying layers than it is to using natural language with LLMs.

Sure doesn't seem like it. https://x.com/jarredsumner/status/1999317065237512224

And forget scripting languages, take a C program that writes a string to disk and reads it back.

How many times longer does it get the moment we have to ensure the string was actually committed to non-volatile NAND and actually read back? 5x? 10x?

Is it even doable if we have to support arbitrary consumer hardware?

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

#348

Post by avereveard »

emseetech wrote: post #323

Everyone's suggestions feel designed to frustrate me. Instructions on how to cajole and plead that seem more astrology than engineering. This is the pattern I settled on about a year ago. I use it as a rubber-duck / conversation partner for bigger picture issues. I'll run my code through it as a sanity "pre-check" before a pr review. And I mapped autocomplete to ctrl-; in vim so I only bring it up when I need it. Oth…

> how to cajole and plead

When a new person join the team you need to tell them the local coding standard. I don't see why people expect llm to work out of the box instead. The difference is you have to do it at every exchange as llm are stateless.

But yeah I mostly agree with the rest llm work best at very low lewel method by method where you can watch like an hawk they don't introduce silent failure condutions and super high level as system design as reasoning engine, and they still do not so good job at implementing components whole.

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

#349

Post by hansmayer »

simonw wrote: post #294
exasperaited wrote: post #263

Earlier quoted context omitted.

> So are animals, but we've used dogs and falcons and truffle hunting pigs as tools for thousands of years. Dogs learn their jobs way faster, more consistently and more expressively than any AI tool. Trivially, dogs understand "good dog" and "bad dog" for example. Reinforcement learning with AI tooling clearly seems not to work.

> Dogs learn their jobs way faster, more consistently and more expressively than any AI tool. That doesn't match my experience with dogs or LLMs at all.

Ever heard of service dogs? Or police dogs? Now tell me, when will LLMs ever be safe to be used as assistance to blind people? Or will the big tech at some point release some sloppy blind-people-tool based on LLMs and unleash the LLM-influencers like yourself to start gaslighting the users into thinking they were "not holding it right" ? For mission and life critical problems, I'll take a dog any day, thank you very much!
Post reply on HN