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

121–130 of 342 posts

Re: How I program with LLMs

#121

Post by Guthur »

wruza wrote: post #103
Guthur wrote: post #93

Earlier quoted context omitted.

Why, what was wrong with code completion, it was perfectly valid before even when including some sort of fuzzing. It's like everything to do with LLM marketing buzzword nonsense. I really want to just drop out of tech until all this obnoxious hype BS is gone.

It’s just a term that signals “completion in between” rather than “after”. Regular code completion usually doesn’t take the following blocks into account mostly because these are grammatically vague due to an ongoing edit. Your comments may be sympathised to, but why on earth are they addressed to the root commenter. They simply shared their findings about an acronym.

Because they mentioned it, why on earth would you think that is not a valid response in a thread that mentions it, from my observation that's pretty much how forum like threads work.

More pressingly why do you think you should police it?

Re: How I program with LLMs

#122

Post by midasz »

simondotau wrote: post #76

I've recently started using Cursor because it means I can now write python where two weeks ago I couldn't write python. It wrote the first pass of an API implementation by feeding it the PDF documentation. I've spent a few days testing and massaging it into a well formed, well structured library, pair-programming style. Then I needed to write a simple command line utility, so I wrote it in Go, even though I've never…

But you're not really writing python right? You're instructing a tool to generate python. Kinda like saying I'm writing bytecode while I'm actually just typing Java.

Re: How I program with LLMs

#123

Post by ignoramous »

dewitt wrote: post #52

One interesting bit of context is that the author of this post is a legit world-class software engineer already (though probably too modest to admit it). Former staff engineer at Google and co-founder / CTO of Tailscale. He doesn't need LLMs. That he says LLMs make him more productive at all as a hands-on developer, especially around first drafts on a new idea, means a lot to me personally. His post reminds me of an…

> [David, Former staff engineer at Google ... CTO of Tailscale,] doesn't need LLMs. That he says LLMs make him more productive at all as a hands-on developer, especially around first drafts on a new idea, means a lot to me...

Don't doubt for a second the pedigree of founding engs at Tailscale, but David is careful to point out exactly why LLMs work for them (but might not for others):

   I am doing a particular kind of programming, product development, which could be roughly described as trying to bring programs to a user through a robust interface. That means I am building a lot, throwing away a lot, and bouncing around between environments. Some days I mostly write typescript, some days mostly Go. I spent a week in a C++ codebase last month exploring an idea, and just had an opportunity to learn the HTTP server-side events format. I am all over the place, constantly forgetting and relearning.

  If you spend more time proving your optimization of a cryptographic algorithm is not vulnerable to timing attacks than you do writing the code, I don't think any of my observations here are going to be useful to you.

Re: How I program with LLMs

#124

Post by Aeolun »

chii wrote: post #57
wdutch wrote: post #27

I no longer work in tech, but I still write simple applications to make my work life easier. I frequently use what OP refers to as chat-driven programming, and I find it incredibly useful. My process starts by explaining a minimum viable product to the chat, which then generates the code for me. Sometimes, the code requires a bit of manual tweaking, but it’s usually a solid starting point. From there, I describe each…

> The code can get messy quickly. There's often a lot of redundancy and after a few iterations it can be quite daunting to modify. i forsee in the future an LLM that has sufficient context length for (automatic) refactoring and tech debt removal, by pasting large portions of these existing code in.

Cursor has recently added something like this ‘Bug Finder’. It told me that finding bugs on my entire codebase would cost me $21 or so, so I never actually tried, but it sounds cool.

Re: How I program with LLMs

#125

Post by Aeolun »

nemothekid wrote: post #28

I think "Chat driven programming" is the most common type of the most hyped LLM-based programming I see on twitter that I just can't relate to. I've incorporated LLMs mainly as auto-complete and search; asking ChatGPT to write a quick script or to scaffold some code for which the documentation is too esoteric to parse. But having the LLM do things for me, I frequently run into issues where it feels like I'm wasting m…

I’ve found that everything just works (more or less) since switching to Cursor. Agent based composer mode is magical. Just give it a few files for context, and ask it to do what you want.

Re: How I program with LLMs

#126

Post by Aeolun »

notjoemama wrote: post #7

Our company has a no AI use policy. The assumption is zero trust. We simply can’t know whether a model or its framework could or would send proprietary code outside the network. So it’s best to assume all LLMs/AI is or will send code or fragments of code. While I applaud the incredible work by their creators, I’m not sure how a responsible enterprise class company could rely on “trust us bro” EULAs or repo readmes.

I mean, we host our code on Github. What are they going to do with Copilot code snippets?

Re: How I program with LLMs

#127

Post by wruza »

Guthur wrote: post #121
wruza wrote: post #103

Earlier quoted context omitted.

It’s just a term that signals “completion in between” rather than “after”. Regular code completion usually doesn’t take the following blocks into account mostly because these are grammatically vague due to an ongoing edit. Your comments may be sympathised to, but why on earth are they addressed to the root commenter. They simply shared their findings about an acronym.

Because they mentioned it, why on earth would you think that is not a valid response in a thread that mentions it, from my observation that's pretty much how forum like threads work. More pressingly why do you think you should police it?

Apologies if my feedback annoyed you, it wasn’t the goal. I just care about HN and this didn’t feel right.

Re: How I program with LLMs

#128

Post by Aeolun »

ripped_britches wrote: post #82

I’ll say that the payoff for investing the time to learn how to do this right is huge. Especially with cursor which allows me to easily chat around context (docs, library files, etc)

I didn’t believe it could be so good until I actually used it. It’s a shame some of their models are proprietary because that means I can’t use it for work. Would love if the thing worked purely with Copilot Chat (like Zed does), or if Zed added a similar composer mode.

Re: How I program with LLMs

#129

Post by devjab »

wiseowise wrote: post #118
devjab wrote: post #110

Earlier quoted context omitted.

I'm genuinely curious but what did you use StackOverflow for before? With a couple of decades in the industry I can't remember when the last time I "Google programmed" anything was. I always go directly to the documentation for whatever it is I'm working for, because where else would I find out how it actually works? It's not like I haven't "Google programmed" when I was younger, but it's just such a slow process bas…

> Why would you go to them rather than the actual documentation? Not every documentation is made equal. For example: Android docs are royal shit. They cover some basic things, e.g. show a button, but good look finding esoteric Bluetooth information or package management, etc. Most of it is a mix of experimentation and historical knowledge (baggage).

> Not every documentation is made equal.

They are wildly different. I'm not sure the Android API reference is that bad, but that is mainly because I've spent a good amount years with the various .Net API references and the Android one is a much more shiny turd than those. I haven't had issues with Bluetooth myself, the Bluetooth SIG has some nice specification PDF's but I assume you're talking about the ones which couldn't be found? I mean this in a "they don't seem to exist" kind of way and not that, you specifically, couldn't find them.

I agree though. It's just that I've never really found internet answers to be very useful. I did actually search for information a few years back when I had to work with a solar inverter datalogger, but it turned out that having the ridicilously long German engineering manual scanned, OCR processed and translated was faster. Anyway, we all have our great white whales. I'm virtually incapable of understanding the SQLAlchemy documentation as an example, luckily I'll probably never have to use it again.

Re: How I program with LLMs

#130

Post by ignoramous »

mlepath wrote: post #2

The first rule of programming with LLMs is don't use them for anything you don't know how to do. If you can look at the solution and immediately know what's wrong with it, they are a time saver otherwise... I find chat for search is really helpful (as the article states)

> ... don't use them for anything you don't know how to do ... I find chat for search is really helpful (as the article states)

Not really. I often use Chat to understand codebases. Instead trying to navigate mature, large-ish FOSS projects (like say, the Android Run Time) by looking at it file by file, method by method, field by field (all to laborious), I just ask ... Copilot. It is way, way faster than I and are mostly directionally correct with its answers.

Post reply on HN