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

361–370 of 491 posts

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

#361

Post by seinecle »

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…

And if I may, these advice also apply if you choose Cursor as a coding environment.

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

#362

Post by _kb »

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…

AIstrology is a term I can get behind.

I think that really captures what I find most irksome about the fanaticism. It's not prompt engineering, it's a statistical 8-ball being shaken until useful output appears.

Just as with any pseudoscience, it can offer a glimmer of usefulness by framing problems in a different way. Just be cautious of who's offering that enlightenment and how much money you may be paying for it.

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

#363

Post by Kubuxu »

danenania wrote: post #184
Kubuxu wrote: post #171

Earlier quoted context omitted.

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.

Definitely agreed, that is what I do as well. At that point you have good understanding of that code, which is in contrast to what the post I responded suggests.

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

#364

Post by ojr »

realberkeaslan wrote: post #2

Consider giving Cursor a try. I personally like the entire UI/UX, their agent has good context, and the entire experience overall is just great. The team has done a phenomenal job. Your workflow could look something like this: 1. Prompt the agent 2. The agent gets too work 3. Review the changes 4. Repeat This can speed up your process significantly, and the UI clearly shows the changes + some other cool features EDIT…

Cursor uses too much memory, hallucinates on multi file rewrites, and has a difficult accept/reject diff user interface that makes git a nightmare to use.

I built my own coding tool in Rust because of VSCode-based forks Electron app flaws. You would think they could build a memory efficient application with the resources they have but it literally needs a top of the line MacBook to run smoothly.

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

#366

Post by simonw »

hansmayer wrote: post #349
simonw wrote: post #294

Earlier quoted context omitted.

> 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…

I've talked to a few people who are blind about vision LLMs and they're very, very positive about them.

They fully understand their limitations. Users of accessibility technology are extremely good at understanding the precise capabilities of the tools they use - which reminds me that screenreaders themselves are a great example of unreliable tools due to the shockingly bad web apps that exist today.

I've also discussed the analogy to service dogs with them, which they found very apt given how easily their assistive tool could be distracted by a nearby steak.

The one thing people who use assistive technology do not appreciate is being told that they shouldn't try a technology out themselves because it's unreliable and hence unsafe for them to use!

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

#367

Post by JackSlateur »

ransom1538 wrote: post #264
eqvinox wrote: post #100

Earlier quoted context omitted.

This is just meaningless knee-jerking, try making an actual argument. At least the GP is arguing that more use of AI leads to loss of personal coding skills. It's unclear at this point what level AI will grow to, i.e. it could hit a hard wall at 70% of a good programmer's ability, and in that case you would really want those personal coding skills since they'll be worth a lot. It could also far exceed a good programm…

"This is just meaningless knee-jerking," Your point is valid. "AI leads to loss of personal coding skills" Unfortunately, I can no longer do long division. No one will pay me to do long division and I have a calculator now. I could stay sharp at long division for a hobby though. Keep those for loops sharp if you want, but I don't see people paying you to hand code. Eventually, it will just be a liability. (like not u…

You think those companies are betting thousands of billions and that's all about code ? Haaha

It is all about money and power

Aka pub and mass control (/propagande)

Another good reason to avoid getting raped by AI (but nothing related to the topic at hand (code))

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

#368

Post by JackSlateur »

Arisaka1 wrote: post #216
ransom1538 wrote: post #95

Earlier quoted context omitted.

This is the fastest way to unemployment benefits (if that is the goal).

Have we really reached the point where a candidate gets outright rejected for not using AI tools, without taking personal aptitudes into consideration?

Last person we recruted, the AI question made our choice

"Are you using AI ?"

(his response, tldr: "yes but actually no, because it sucks")

Great collaborator

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

#369

Post by aiisahik »

Hey there.

Most of the advice here focuses on Claude Code. Since your use case revolves around a very specific frameworks and refactoring workflow, my advice is to use AI tooling that will allow you to experiment with other models.

Opus 4.5 is my fav it simply can't be the best for every use case. My advice is to use cursor and switch between the various SOTA models to see which one serves your use case the best.

I'm not sure if you can also build something using AI that will help you automatically determine if the outputted component matches the Storybook story. That would be the first thing i try.

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

#370

Post by ram_shares »

What improved results for me was forcing a two-step loop:

Step 1: Ask the model to outline component boundaries, data flow, and edge cases — no code. Step 2: Only after approving the plan, let it generate code for one component at a time.

When I skip the planning step, the output is usually “working but unidiomatic”. With it, reviews get much faster.

Post reply on HN