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

351–360 of 491 posts

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

#351

Post by hansmayer »

simonw wrote: post #341
hansmayer wrote: post #338

Earlier quoted context omitted.

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 pro…

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

Firstly, I am not the one with an LLM-influencer side-gig. Secondly - No sorry, please don't move the goalposts. You did not answer my main argument - which is - how does a "tool" which constantly change its behaviour deserve being called a tool at all? If a tailor had scissors which cut the fabric sometimes just a bit, and sometimes completely differently every time they used it, would you tell the tailor he is not using them right too? Thirdly you are now contradicting yourself. First you said we need to live with the fact that they are un-predictable. Now you are sugarcoating it into being "a bit unpredictable", or "not as nearly unpredictable". I am not sure if you are doing this intentionally or do you really want to believe in the "magic" but either way you are ignoring the ground tenets of how this technology works. I'd be fine if they used it to generate cheap holiday novels or erotica - but clearly after four years of experimenting with the crap machines to write code created a huge pushback in the community - we don't need the proverbial scissors which cut our fabric differently each time!

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

#352

Post by baq »

hansmayer wrote: post #210
kfajdsl wrote: post #206

Earlier quoted context omitted.

It's a tool. The first time you used a shell you had to learn it. The first time you used a text editor you had to learn it. You can learn how to use it, or you can put it down if you think it doesn't bring you any benefit.

I am sorry but what do I have to learn? That the tool does not work as advertised? That sometimes it will work as advertised, sometimes not? That it will sometimes expose critical secrets as plain text and some other time suggest to solve a problem in a function by removing the function code completely? What are you even talking about, comparing to shell and text editors? These are still bloody deterministic tools. Y…

You’ve asked the right questions and don’t want to find the answers. It’s on you.

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

#353

Post by ehnto »

avereveard wrote: post #348
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…

Both human and AI should be able to understand the "way we do things around here" by reading the existing code. I could spend an hour telling someone how to write idiomatic code, and they will forget all of it until they actually do some work and see the codebase.

When Claude reads a significant portion of my codebase into context it should be suggesting idiomatic changes. Even if it doesn't initially read a bunch of the codebase to figure out a solution, it should definitely then be trained to do so explicitly to understand the coding standards. Just like a decent dev would do on their own.

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

#354

Post by verdverm »

skeptrune wrote: post #297

You should make sure that your queries to the agent contain a "loop condition"[1]. This can be something like "keep trying until yarn test passes". Always remember that these agents are just LLMs running tools in a loop and treat them as such. [1] https://www.skeptrune.com/posts/prompting-the-agent-loop/

if they aren't already, they will be multi-agent / llm systems, more and llm being asked to loop

for example, in ADK you can set up a sequential agent with [planner, loop(coder, validator), finalizer] with the inner loop, such that another agent is the one checking and deciding if the task is complete or not, but we are also creating higher level enforced constructs of seq and loop

Getting reliability in this high-level process is helpful

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

#355

Post by blobbers »

hanska wrote: post #161
dotancohen wrote: post #101

Earlier quoted context omitted.

That is seriously short. I've asked Claude Code to add instructions to CLAUDE.md and my one line request has resulted in tens of lines added to the file.

yes if you tell llm to do things it will be too verbose. either explicitly instruct the length ("add 5 lines bulletpoints, tldr format") or just write it yourself.

Seems reasonable to give Claude instructions to be extra terse.

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

#356

Post by bcherny »

sahilagarwal wrote: post #329
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…

Hi Boris, If you wouldn't mind answering a question for me, it's one of the main things that has made me not add claude in vscode. I have a custom 'code style' system prompt that I want claude to use, and I have been able to add it when using claude in browser - ``` Beautiful is better than ugly. Explicit is better than implicit. Simple is better than complex. Complex is better than complicated. Readability counts. S…

Add it to your CLAUDE.md. Claude will automatically read that file every time it starts up

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

#357

Post by bcherny »

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).

Since we released the last major version of Claude Code, Claude writes its plan to a file automatically for that reason! It also means you can continue to edit your plan as you go.

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

#358

Post by ehnto »

BoorishBears wrote: post #332
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.

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…

I don't buy your past paragraph at all I am afraid. Coding langues, even high level ones, are built upon foundations of determism and they are concise and precise. A short way to describe very precisely, a bunch of rules and state.

Prompting is none of those things. It is a ball of math we can throw words into, and it approximates meaning and returns an output with randomness built in. That is incredible, truly, but it is not a programming language.

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

#359

Post by verdverm »

ebcode wrote: post #137
daxfohl wrote: post #55

Go slowly. Shoot for a 10% efficiency improvement, not 10x. Go through things as thoroughly as if writing by hand, and don't sacrifice quality for speed. Be aware of when it's confidently taking you down a convoluted path and confidently making up reasons to do so. Always have your skeptic hat on. If something seems off, it probably is. When in doubt, exit the session and start over. I still find chat interface gener…

> A 10% improvement every month gets to be a 10x improvement in (math...) 1.1^24=9.85, so yeah, if you could reliably get a 10% speed-up each month, you’d get to 10x in roughly 2 years. (But I’d expect the speed-up per month to be non-linear.)

it would be hard to account for model / agentic capability increases in the next 2 years, b/c which side of multiple Nx on its own is hard to predict

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

#360

Post by simonw »

hansmayer wrote: post #351
simonw wrote: post #341

Earlier quoted context omitted.

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 pro…

> One of us is misleading people here, and I don't think it's me. Firstly, I am not the one with an LLM-influencer side-gig. Secondly - No sorry, please don't move the goalposts. You did not answer my main argument - which is - how does a "tool" which constantly change its behaviour deserve being called a tool at all? If a tailor had scissors which cut the fabric sometimes just a bit, and sometimes completely differe…

> how does a "tool" which constantly change its behaviour deserve being called a tool at all?

Let's go with blast furnaces. They're definitely tools. They change over time - a team might constantly run one for twenty years but still need to monitor and adjust how they use it as the furnace itself changes behavior due to wear and tear (I think they call this "drift".)

The same is true of plenty of other tools - pottery kilns, cast iron pans, knife sharpening stones. Expert tool users frequently use tools that change over time and need to be monitored and adjusted.

I do think dogs and horses other animal tools remain an excellent example here as well. They're unpredictable and you have to constantly adapt to their latest behaviors.

I agree that LLMs are unpredictable in that they are non-deterministic by nature. I also think that this is something you can learn to account for as you build experience.

I just fed this prompt to Claude Code:

  Add to_text() and to_markdown() features to justhtml.html - for the whole document or for CSS selectors against it
  
  Consult a fresh clone of the justhtml Python library (in /tmp) if you need to
It did exactly what I expected it would do, based on my hundred of previous similar interventions with that tool: https://github.com/simonw/tools/pull/162
Post reply on HN