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

321–330 of 491 posts

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

#321

Post by hebrox »

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).

I ask it to write a plan and when it starts the work, keep progress in another document and to never change the plan. If I didn't do this, somehow with each code change the plan document would grow and change. Keeping plan and progress separate prevented this from happening.

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

#322

Post by eqvinox »

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…

> Keep those for loops sharp if you want, but I don't see people paying you to hand code.

Well, personally speaking, I'm paid to hand code; LLMs have not reached the quality of my code output yet and I'm seeing no pressure at all to use LLMs.

Relatedly, I work on an open source project where the constraining resource is review (as it is in most open source projects.) The current state is that LLM generated code is incredibly hard and annoying to review and there is a lot of pushback.

So, I'm going to wait and see.

(...especially since there's also legal challenges to LLMs trained on open source code with no regard to its licenses.)

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

#323

Post by emseetech »

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.

Otherwise, I write everything myself. AI written code never felt safe. It adds velocity but velocity early on always steals speed from the future. That's been the case for languages, for frameworks, for libraries, it's no different for AI.

In other words, you get better at using AI for programming by recognizing where its strengths lie and going all in on those strengths. Don't twist up in knots trying to get it to do decently what you can already do well yourself.

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

#325

Post by grim_io »

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…

I don't think anyone would say that the LLMs will produce better code, but they can do it much faster.

I personally did not hit the wall where the use of LLMs would slow me down in the long run.

It has been smooth sailing most of the time, and getting better with newer models.

For me it comes down to "know what you are being paid for".

I'm not a library maintainer. My code will not be scrutinized by thousands of peers. My customer will be happy with faster completion that does the same thing like the more perfect hand crafted version.

Welcome to the industrial revolution in programming. This is the way of things.

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

#326

Post by sahilagarwal »

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…

Same. AI is a good tool to use as a sounding board and conversation partner.

I only access claude and others using my browser - I give it a snippet of my code, tell it what exactly I want to do and what my general goal is, then ask it to give me approaches, and their pros and cons.

Even if someone wants to use AI to code for them, its still better to do the above as a first step imo. A sort of human in the loop system.

> It adds velocity but velocity early on always steals speed from the future. That's been the case for languages, for frameworks, for libraries, it's no different for AI.

Completely agree. I'm seeing this in my circle and workplace. My velocity might be a tad bit slower than the rest of my peers when you compare it per ticket. But my long tern output hasn't changed and interestingly, neither has anyone else's.

As an aside, I like your system of completely removing autocomplete unless you need it - may be something like that would finally get me to enable AI in my IDE.

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

#327

Post by seanmcdirmid »

If you are working on something big, have AI generate intermediate artifacts before it generates code, and feed those artifacts into the code generation prompt. Then you check those artifacts, see where the AI is going with the code, and suggest corrections before a token of code is even generated. Keep those artifacts around like you would documentation, having your AI fix them when the code needs to change.

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

#328

Post by mrieck »

manmal wrote: post #217
glamp wrote: post #185

Earlier quoted context omitted.

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 fin…

Why don’t you reset context when working on something else?

It’s additional features that are related.

For example making a computer use agent… Made the plan, implementation was good, now I want to add a new tool for the agent, but I want to discuss best way to implement this tool first.

Clearing context means Claude forgets everything about what was just built.

Asking to discuss this new tool in plan mode makes Claude rewrite entire spec for some reason.

As workaround, I tell Claude “looks good, delete the plan” before doing anything. I liked the old way where once you exit plan mode the plan is done, and next plan mode is new plan with existing context.

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

#329

Post by sahilagarwal »

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. Special cases aren't special enough to break the rules. Although practicality beats purity. If the implementation is hard to explain, it's a bad idea. If the implementation is easy to explain, it may be a good idea.

Trust the context you're given. Don't defend against problems the human didn't ask you to solve. ```

How can I add it as a system prompt (or if its called something else) in vscode so LLMs adhere to it?

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

#330

Post by lkjdsklf »

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…

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.

Post reply on HN