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

251–260 of 491 posts

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

#251

Post by fastball »

kelvinjps10 wrote: post #243
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…

How do you make Claude code to choose opus and not sonnet? For me it seems to do it automatically

/model

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

#252

Post by handfuloflight »

bakugo wrote: post #250
handfuloflight wrote: post #222

Earlier quoted context omitted.

That $200 a month is getting me $2000 a month in API equivalent tokens. I used to spend $200+ an hour on a single developer. I'm quite sure that benevolence was a factor when they submitted me an invoice, since there is no real transparency if I was being overbilled or not or that the developer acted in my best interest rather than theirs. I'll never forget that one contractor who told me he took a whole 40 hours to…

> That $200 a month is getting me $2000 a month in API equivalent tokens. Do you ever feel bad for basically robbing these poor people blind? They're clearly losing so much money by giving you $1800 in FREE tokens every month. Their business can't be profitable like this, but thankfully they're doing it out of the goodness of their hearts.

I'm not sure that you actually expect to be taken seriously if you're going to assert that these companies don't have costs themselves to deliver their services.

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

#253

Post by thyb23 »

Spent a lot of time experimenting with different AI coding tools (Claude Code, Gemini CLI, Cursor, Codex CLI, Antigravity...). Boris's tips cover 90% of what I'd say.

The most important is to use Claude Code with Claude Max plan to have almost unlimited access to Opus 4.5 :) the agent and DX is top notch. It one shot most of my tasks with correct code quality. If you prefer Cursor like DX, you can use Zed with the free Claude Code integration in its UI. Before, I was multiplying $20 plans but it was really annoying to switch between products to get worse quality than Opus. Best investment I made this year.

Then as Boris told: give the model a way to verify its work, just telling it explicitly 'to test, run X command / check the db in container Y / make curl request with Z access token to test your endpoint'. Game changer.

Don't overload context. When switching tasks, clear and start fresh. Mixing old task context with new one creates confusion and worse output.

One observation on Gemini 3 vs Claude 4.5 Opus: Gemini is great for one-shot on fresh projects and UIs, but struggles more on large codebases and can get easily confused (might be the Windsurf agent though).

Just experiment a lot. Like coding itself, you build intuition over time on what works and what doesn't.

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

#254

Post by majewsky »

amirhirsch wrote: post #221
MontyCarloHall wrote: post #169

Earlier quoted context omitted.

Good question. Why hasn't there been a profusion of new game-changing software, fixes to long-standing issues in open-source software, any nontrivial shipped product at all? Heck, why isn't there a cornucopia of new apps, even trivial ones? Where is all the shovelware [0]? Previous HN discussion here [1]. Don't get me wrong, AI is at least as game-changing for programming as StackOverflow and Google were back in the…

The effect of these tools is people losing their software jobs (down 35% since 2020). Unemployed devs aren’t clamoring to go use AI on OSS.

Wasn't most of that caused by that one change in 2022 to how R&D expenses are depreciated, thus making R&D expenses (like retaining dev staff) less financially attractive?

Context: This news story https://news.ycombinator.com/item?id=44180533

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

#255

Post by majewsky »

Bjartr wrote: post #70
thfuran wrote: post #61

Earlier quoted context omitted.

But that documentation shouldn’t need to be updated nearly every other day.

Consider that every time you start a session with Claude Code. It's effectively a new engineer. The system doesn't learn like a real person does, so for it to improve over time you need to manually record the insights that for a normal human would be integrated by the natural learning process.

Yes, that's exactly the problem. There's good reasons why any particular team doesn't onboard new engineers each day, going all the way back to Fred Brooks and "adding more people to a late project makes it later".

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

#256

Post by bdangubic »

Bjartr wrote: post #70
thfuran wrote: post #61

Earlier quoted context omitted.

But that documentation shouldn’t need to be updated nearly every other day.

Consider that every time you start a session with Claude Code. It's effectively a new engineer. The system doesn't learn like a real person does, so for it to improve over time you need to manually record the insights that for a normal human would be integrated by the natural learning process.

there are many tools available that work towards solving this problem

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

#257

Post by xn »

simonw wrote: post #247
hansmayer wrote: post #210

Earlier quoted context omitted.

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…

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.

It's like having Michael Jordan with dementia on your team. You start out mesmerized by how many points he can score, and then you get incredibly frustrated that he forgets he has to dribble and shoot into the correct hoop.

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

#258

Post by heavyset_go »

shsush wrote: post #160
matt3210 wrote: post #126

Earlier quoted context omitted.

Can you show some example? I feel like there would be streams or YouTube lets plays on this if it was working well

The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing. Very pro agent devs like ghuntley will all say this. And it makes sense. For most coding problems the challenge isn’t writing code. Once you know what to write typing the code is a drop in the bucket. AI is still very useful, but if you really wanna go fast you have to give up on you…

> The real secret to agent productivity is letting go of your understanding of the code

This is negligence, it's your job to understand the system you're building.

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

#259

Post by roughly »

epolanski wrote: post #117
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…

> 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…

One of the things you get an intuition for after using these systems is when to start a new conversation, and the basic rule of thumb is “always.” Use a conversation for one and only one task or question, and then start a new one. For longer projects, have the LLM write down a plan or checklist, and then have it tackle each step in a new conversation. The LLM context collapse happens well before you hit the token limits, and things like ground rules and whatnot stop influencing the LLMs outputs after a couple tens of thousands of tokens in my experience.

(Similar guidance goes for writing tools & whatnot - give the LLM exactly and only what it needs back from a tool, don’t try to make it act like a deterministic program. Whether or not they’re capital-I intelligent, they’re pretty fucking stupid.)

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

#260

Post by topaz0 »

PostOnce wrote: post #219

If anyone knew the answer to this question, Anthropic would be profitable. Currently they project they might break even in 2028. That means that right now, every time you ask an AI a question, someone loses money. That of course means no-one knows if you can get better at AI programming, and the answer may be "you can't." Only time will tell.

And that projection is mostly based on wishes and dreams.
Post reply on HN