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

441–450 of 491 posts

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

#441

Post by xpe »

mrwrong wrote: post #403
justatdotin wrote: post #249

Earlier quoted context omitted.

my starting point was Google People Management Essentials. I was thinking about team-level politics at work, and noticed some ideas seemed relevant to how teams in orgs can adopt agents. I pursued that idea more widely with other resources and it resonated. I don't think I have any conclusions to share, just the orientation: to identify and actively accommodate the tool's cognitive style in the same way we do for one…

your suggestion is to treat it like a person but (surprise surprise) you don't have any specific ideas of how and why that works. your idea just sounds like marketing

> your suggestion is to treat it like a person but (surprise surprise) you don't have any specific ideas of how and why that works. your idea just sounds like marketing

This is unnecessarily mean. Please review https://news.ycombinator.com/newsguidelines.html

> Be kind. Don't be snarky. Converse curiously; don't cross-examine. Edit out swipes.

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

#442

Post by avereveard »

ehnto wrote: post #353
avereveard wrote: post #348

Earlier quoted context omitted.

> 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…

if you'd be right that code is so self evident project wouldn't have a coding.md or a contributing.md

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

#443

Post by hbrn »

ImPostingOnHN wrote: post #412
simonw wrote: post #360

Earlier quoted context omitted.

> 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 - potter…

> 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 distinguish marketing message vs real value. But in terms of bang for buck, Claude Code is an absolute blast (pun intended)!

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

#444

Post by somangshu »

Hey, I am the co-founder at https://brew.studio We built the platform for the problem you are facing. Our agent `brew` excels at managing context with growing change requests and actual code change so that solving spaghetti code is easier and efficient.

We will allow you to create and supervise impact analysis on a change request you are planning and then you get brew to also create a detailed implementation prompt for you. This way you always remain in control and our able to instruct you AI coding agent better at once.

Not just this, we also map the commit that comes in to the original change request and show you what's done, what's not, Expected vs Actual & unplanned changes mapping them to actual code that is written. This makes it really easy to review.

We are in our early stages. I would love for you to try us out. I am open to offering you usage credits as well.

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

#445

Post by potatoman22 »

BoiledCabbage wrote: post #345
potatoman22 wrote: post #340

Earlier quoted context omitted.

It's technically deterministic, but it feels nondeterministic in chatbots since tokens are randomly sampled (temp > 0) and input is varied. Using the right prompt makes the model perform better on average, so it's not completely dumb. I like task vectors and soft prompts because I think they show how prompt engineering is cool and useful. https://arxiv.org/pdf/2310.15916 https://huggingface.co/docs/peft/conceptual_gu…

> It's technically deterministic, but it feels nondeterministic in chatbots since tokens are randomly sampled Are you not aware the random sampling makes something non-deterministic?

I'm saying LLMs are deterministic and because of that, prompt engineering can be effective. You knew what I was trying to say, but chose to ignore it.

You should follow the HN Guidelines. I'm trying to have a discussion, not a snarkfest.

> Be kind. Don't be snarky. Converse curiously; don't cross-examine. Edit out swipes.

> Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith.

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

#446

Post by nineteen999 »

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…

for i in seq(1,100) ; do cat CLAUDE.md ; done

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

#447

Post by potatoman22 »

rTX5CMRXIfFG wrote: post #380
BoiledCabbage wrote: post #345

Earlier quoted context omitted.

> It's technically deterministic, but it feels nondeterministic in chatbots since tokens are randomly sampled Are you not aware the random sampling makes something non-deterministic?

I don’t believe that when he wrote that, he was using his own intelligence

At least I'm adding to the discussion.

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

#448

Post by rTX5CMRXIfFG »

potatoman22 wrote: post #447
rTX5CMRXIfFG wrote: post #380

Earlier quoted context omitted.

I don’t believe that when he wrote that, he was using his own intelligence

At least I'm adding to the discussion.

People who disagree with you add to the discussion too

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

#449

Post by BoorishBears »

lifeformed wrote: post #399
BoorishBears wrote: post #392

Earlier quoted context omitted.

- A text prompt isn't probabilistic, the output is. - https://labs.oracle.com/pls/apex/f?p=LABS:0:5033606075766:AP... - https://en.wikipedia.org/wiki/Stan_(software) - https://en.wikipedia.org/wiki/Probabilistic_programming I explained in the most clear language possible why a fixation on the "programming language" part of the original comment is borderline non-sequitur. But if you're insistent on railroading the con…

I skimmed your comment since you were making the strange comparison that modern coding is basically probabilistic to a degree that prompting is, so I see now you weren't the one to say it's "probabilistic programming". But you are still trying to say that normal programming is basically probabilistic in some relevant way, which I think is quite ridiculous. I don't see how anything about normal engineering is probabil…

"I didn't do the absolute bare minimum and read the comment I replied to, so here's 100 words excusing that."
Post reply on HN