Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How I program with LLMs

crawshaw.io

Post reply on HN
Print view View original

311–320 of 342 posts

Re: How I program with LLMs

#311

Post by brabel »

ryanobjc wrote: post #282
brabel wrote: post #98

What the author is asking about, a quick sketchpad where you can try out code quickly and chat with the AI, already exists in the JetBrains IDEs. It's called a scratch file[1]. As far as I know, the idea of a scratch "buffer" comes from emacs. But in Jetbrains IDEs, you have the full IDE support even with context from your current project (you can pick the "modules" you want to have in context). Given the good integr…

It's also available in emacs with packages like gptel which let you send the content of any buffer to your LLM of choice. I think emacs + LLM is a killer feature: the integration is super deep, deeper than any IDE I've seen, and it's just available... everywhere! Any text in emacs is sendable to a LLM.

I need to try that, but I have a feeling that in emacs it won't work as well because emacs has a bit more "trouble" setting up workspaces and using context only from that. Trying use use `project.el` now as it seems projectile has been superseded by it, if you know how to easily set that up with eglot support + AI would be helpful.

Re: How I program with LLMs

#312

Post by IanCal »

fastball wrote: post #303
IanCal wrote: post #165

Earlier quoted context omitted.

I understand what it's doing, and could easily set out the cases I needed.

If you understand what it is doing, you could do it yourself, surely?

Have you never understood the solution to a puzzle much more easily than solving it yourself? I feel there's literally a huge branch of mathematics dedicated to the difference between finding and validating a solution.

More specifically, I didn't know how to solve it, though obviously could have spent much more time and learned. There were only a small number of possible cases, but I needed certain ones to work and others not to. I was easily able to create the examples but not find the solution. With looping through claude I could solve it in a few minutes. I then got an explanation, could read the right relevant docs and feel satisfied that not only did everything pass the automated checks but my own reasoning.

Re: How I program with LLMs

#313

Post by wizzard0 »

Ygg2 wrote: post #142

> Search. If I have a question about a complex environment, say “how do I make a button transparent in CSS” I will get a far better answer asking any consumer-based LLM, than I do using an old fashioned web search engine. I don't think this is about LLMs getting better, but search becoming worse. In no small thanks to LLMs polluting the results. Do search images for terms and count how many are AI generated. I can sa…

Google gets money from showing you ads, not because you pay them for quality search results.

When you have to come over and over, and visit more pages to finally find what you needed, they get much more cash from advertisers than when you get everything instantly.

Re: How I program with LLMs

#314

Post by amenhotep »

Vampiero wrote: post #285
HappMacDonald wrote: post #272

Earlier quoted context omitted.

So just to make sure I'm on the same page: you're bemoaning how commonly people abbreviate uncommon sayings?

I'm bemoaning the fact that I have to google random acronyms every time an American wants to say the most basic shit as if everyone on the internet knows their slang and weird four letter abbreviations And googling those acronyms usually returns unrelated shit unless you go specifically to urban dictionary And then it's "If I understand correctly". Oh. Of course. He couldn't be arsed to type that

FWIW IMO YTA

Re: How I program with LLMs

#315

Post by edgineer »

amenhotep wrote: post #314
Vampiero wrote: post #285

Earlier quoted context omitted.

I'm bemoaning the fact that I have to google random acronyms every time an American wants to say the most basic shit as if everyone on the internet knows their slang and weird four letter abbreviations And googling those acronyms usually returns unrelated shit unless you go specifically to urban dictionary And then it's "If I understand correctly". Oh. Of course. He couldn't be arsed to type that

FWIW IMO YTA

frfr

Re: How I program with LLMs

#316

Post by theptip »

This lines up well with my experience. I’ve tried coming at things from the IDE and chat side, and I think we need to merge tooling more to find the sweet spot. Claude is amazing at building small SPAs, and then you hit the context window cutoff and can’t do anything except copy your file out. I suspect IDEs will figure this out before Claude/ChatGPT learn to be good enough at the things folks need from IDEs. But long-term, i suppose you don’t want to have to drop down to code at all and so the constraints of chat might force the exploration of the new paradigm more aggressively.

Hot take of the day, I think making tests and refactors easier is going to be revolutionary for code quality.

Re: How I program with LLMs

#317

Post by arminiusreturns »

psychoslave wrote: post #307
arminiusreturns wrote: post #216

Earlier quoted context omitted.

After a small prompt engineering: https://0bin.net/paste/zolMrjVz#dgZrZzKU-PlxdkJTdG0pZU9bsCM3...

Interesting, thanks for sharing. Could you also give some insights on the process you followed?

Sure. Lately I've found that the "role" part of prompt engineering seems to be the most important. So what I've been doing is telling ChatGPT to play the role of the most educated/wise/knowledgeable/skilled $field $role(advisor, lawyer, researcher etc) in the history of the world and then giving it some context for the task before asking for the actual task.

Sometimes asking it to self reflect on how the prompt itself could be better engineered helps if the initial response isn't quite right.

Re: How I program with LLMs

#318

Post by mbesto »

aulin wrote: post #306
klibertp wrote: post #296

Earlier quoted context omitted.

Please acknowledge that your situation is pretty unique. Just take a look at the comments: how many people say, or outright presume, that their company's code is already on GitHub? I'd wager that your org doesn't keep code at a 3rd party provider, right? Then, you're in a minority. I don't mean to dismiss your concerns - in your situation, they are probably warranted - I just wanted to say that they are unique and no…

This subthread started with someone from a no AI policy company, people are dismissing it with snarky comments, along the line of your code is not as important as you believe. I'm just trying to show a different picture, we work in a pretty vast field and people commenting here don't necessarily represent a valid sample.

First, I didn't dismiss their "no AI policy" nor did I use snarky comments. I was asking a legitimate question - which is - most orgs have their code stored on another server out of their control, so what's the legitimate business issue if your code gets leaked? I still haven't gotten an answer.

Re: How I program with LLMs

#319

Post by mbesto »

aulin wrote: post #309
klibertp wrote: post #308

Earlier quoted context omitted.

> people are dismissing it with snarky comments, along the line of your code is not as important as you believe. That says more about those people than about your/OP's code :) Personally, I had a few collisions with regulation and compliance over the years, so I can appreciate the completely different mindset you need when working with them. On the other hand, at my current position, not only do we have everything on…

Yes I've had plenty of experiences with orgs that self host everything, I don't think it's a minority it's just a different cluster than the one most represented here. Still I believe hosting is somewhat different, if anything because it's something established, known players, trusted practices. AI is new, contracts are still getting refined, players are still making their name, companies are moving fast and I doubt…

> Yes I've had plenty of experiences with orgs that self host everything, I don't think it's a minority it's just a different cluster than the one most represented here.

I've done 800+ tech diligence projects and have first hand knowledge of every single one's use of VCS. At least 95% of the codebases are stored on a cloud hosted VCS. It's absolutely a minority to host your own VCS.

Re: How I program with LLMs

#320

Post by mbesto »

aulin wrote: post #309
klibertp wrote: post #308

Earlier quoted context omitted.

> people are dismissing it with snarky comments, along the line of your code is not as important as you believe. That says more about those people than about your/OP's code :) Personally, I had a few collisions with regulation and compliance over the years, so I can appreciate the completely different mindset you need when working with them. On the other hand, at my current position, not only do we have everything on…

Yes I've had plenty of experiences with orgs that self host everything, I don't think it's a minority it's just a different cluster than the one most represented here. Still I believe hosting is somewhat different, if anything because it's something established, known players, trusted practices. AI is new, contracts are still getting refined, players are still making their name, companies are moving fast and I doubt…

> I doubt data protection is their priority.

So you're basing your whole argument on nothing other than "I just don't feel like they do that".

Does this look unserious to you? https://trust.openai.com/

Post reply on HN