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

461–470 of 491 posts

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

#461

Post by theshrike79 »

SV_BubbleTime wrote: post #191
epolanski wrote: post #117

Earlier quoted context omitted.

> 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. Sure, for 4/5 interactions then will ignore those completely :) Try for yourself: add to CLAUDE.md an instruction to always refer to you as Mr. bcherny and it will stop very soon. Coincidentally at that…

The number of times I’ve written “read your own fucking Claude.md file” is a bit too numerous. “You’re absolutely right! I see here you don’t want me to break every coding convention you have specified for me!”

How long are your conversations with Claude?

I've used it pretty extensively over the year and never had issues with this.

If you hit autocompact during a chat, it's already too long. You should've exported the relevant bits to a markdown file and reset context already.

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

#462

Post by jrussellaz »

dmd wrote: post #406
koolba wrote: post #316

Earlier quoted context omitted.

I’m old enough to remember being able to work at programming related tasks without any such tools. Is that not still a thing?

I obviously meant "work with it" not work in general. And as for old, I'm 47. I've been programming since I got my first C64 in 1985.

Hey dmd!

Same here, 47 and got my start programming on a Commodore 64. What’s up, brother?

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

#463

Post by theshrike79 »

lostdog wrote: post #205
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…

Yes, I've also been confused by things like this. Claude code is sometimes saving plans to ~/.claude/plans under animal names. But it's not really surface where the plan goes, not what the expected way to refer back to them is?

It's a cache pretty much. Before it wrote them to the project directory by default, which is really annoying.

Now it has a file it can refer to (call it "memory" to be fancy) without having to keep everything in context. The plan in the file survives over autocompact a lot better and it can just copy it to the project directory without rewriting it from memory.

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

#465

Post by chrz »

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…

The coding standard is quality code and one should bring it with themselves comming into the company. And if you mean linter & formatting rules then if company is not young then their elders had a fist fight to settle once and for all one standard, zip it into a file and everybody just use it

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

#466

Post by theshrike79 »

koolba wrote: post #316
dmd wrote: post #116

Earlier quoted context omitted.

I would LOVE to use Opus 4.5, but it means I (a merely Pro peon) can work for maybe 30 minutes a day, instead of 60-90.

I’m old enough to remember being able to work at programming related tasks without any such tools. Is that not still a thing?

I didn't enjoy spending two nights fighting with a shitty API and trying to figure out why it doesn't work.

Now I can do it with Claude within minutes, while watching my TV shows on the second monitor and get directly to the good bits, the actual "business logic" of whatever I'm building.

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

#467

Post by dmd »

jrussellaz wrote: post #462
dmd wrote: post #406

Earlier quoted context omitted.

I obviously meant "work with it" not work in general. And as for old, I'm 47. I've been programming since I got my first C64 in 1985.

Hey dmd! Same here, 47 and got my start programming on a Commodore 64. What’s up, brother?

CHR$($91)

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

#468

Post by thehours »

johnfn wrote: post #15
bogtog wrote: post #10

Using voice transcription is nice for fully expressing what you want, so the model doesn't need to make guesses. I'm often voicing 500-word prompts. If you talk in a winding way that looks awkward when in text, that's fine. The model will almost certainly be able to tell what you mean. Using voice-to-text is my biggest suggestion for people who want to use AI for programming (I'm not a particularly slow typer. I can…

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 the Raycast + Whisper Dictation. I don't think there is anything novel about it, but it integrates nicely into my workflow.

My main gripe is when the recording window loses focus, I haven't found a way to bring it back and continue the recorded session. So occasionally I have to start from scratch, which is particularly annoying if it happens during a long-winded brain dump.

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

#469

Post by ImPostingOnHN »

hbrn wrote: post #443
ImPostingOnHN wrote: post #412

Earlier quoted context omitted.

> 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".) Now let's make the analogy more accurate: let's imagine the blast furnace often ignores the operator controls, and just did what it "wanted" i…

> What a weird blast furnace! Would anyone try to use this tool in such a scenario? Not most experienced metalworkers. Absolutely wrong. If this blast furnace would cost a fraction of other blast furnaces, and would allow you to produce certain metals that were too expensive to produce previously (even with high error rate), almost everyone would use it. Which is exactly what we're seeing right now. Yes, you have to…

> this blast furnace would cost a fraction of other blast furnaces

Totally incorrect: as we already mentioned, this blast furnace actually costs just as much as every other blast furnace to run all the time (which they do). The difference is only in the outputs, which I described in my post and now repeat below, with emphasis this time.

Let's also imagine that the blast furnace changes behavior minute-to-minute (usually in the middle of the process) between useful output, useless output (requires scrapping), and counterproductive output ——>(requires rework which exceeds the productivity gains of using the blast furnace to begin with)

Does this describe any currently-operating blast furnaces you are aware of? Like I said, probably not, for good reason.

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

#470

Post by jcheng »

cerved wrote: post #439
jcheng wrote: post #218

Earlier quoted context omitted.

Personally, CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR=1 made all my cd problems go away (which were only really in cmake-based projects to begin with).

So it does a forced reset of the dirt after each bash command? Does it confuse Claude? I frequently find it lacks path awareness of what it's working directory is

That’s exactly what it does, I’ve found it completely un-confuses Claude Sonnet 4.5.
Post reply on HN