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

131–140 of 342 posts

Re: How I program with LLMs

#131

Post by Aeolun »

wrs wrote: post #4

I’ve been working with Cursor’s agent mode a lot this week and am seeing where we need a new kind of tool. Because it sees the whole codebase, the agent will quickly get into a state where it’s changed several files to implement some layering or refactor something. This requires a response from the developer that’s sort of like a code review, in that you need to see changes and make comments across multiple files, bu…

I think the full agent mode context is actually often hard to see, but there’s a list somewhere. The list of files in your chat dialog is not the full context (it adds open files too). I find that if I reduce the context size Cursor gives me much better results.

Re: How I program with LLMs

#132

Post by liotier »

gopalv wrote: post #88
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…

> 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. There is likely to be a great rift in how very talented people look at sharper tools. I've seen the same division pop up with CNC machines, 3d printers, IDEs and now LLMs. If you are good at doing something, you might find the new tool's output to be sub-par over wha…

> If you are good at doing something, you might find the new tool's output to be sub-par over what you can achieve yourself, but often the lower quality output comes much faster than you can generate. That causes the people who are deliberate & precise about their process to hate the new tool completely

Wow, I've been there ! Years ago we dragged a GIS system kicking and screaming from its nascent era of a dozen ultrasharp dudes with the whole national fiber optics network in their head full of clever optimizations, to three thousand mostly clueless users churning out industrial scale spaghetti... The old hands wanted a dumb fast tool that does their bidding - they hated the slower wizard-assisted handholding, that turned out to be essential to the new population's productivity.

Command line vs. GUI again... Expressivity vs. discoverability, all the choices vs. don't make me think. Know your users !

Re: How I program with LLMs

#133

Post by stevage »

This is a great article with lots of useful insights.

But I'm completely unconvinced by the final claim that LLM interfaces should be separate from IDE's, and should be their own websites. No thanks.

Re: How I program with LLMs

#134

Post by tomwojcik »

ilrwbwrkhv wrote: post #111
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…

Being a dev at a large company is usually the sign that you're not very good though. And anyone can start a company with the right connections.

That's a terrible blanket statement, very US-centric. Not everyone wants to start a company and you can't just reduce ones motivations to your measure of success.

Re: How I program with LLMs

#135

Post by dxuh »

Currently a lot of my work consists of looking at large, (to me) unknown code bases and figuring out how certain things work. I think LLMs are currently very bad at this and it is my understanding that there are problems in increasing context window sizes to multiple millions of tokens, so I wonder if LLMs will ever get good at this.

Re: How I program with LLMs

#136

Post by fragmede »

mmahemoff wrote: post #77
Ozzie_osman wrote: post #71

One mode I felt was missed was "thought partner", especially while debugging (aka rubber ducking). We had an issue recently with a task queue seemingly randomly stalling. We were able to arrive at the root cause much more quickly than we would have because of a back-and-forth brainstorming session with Claude, which involved describing the issue we were seeing, pasting in code from library to ask questions, asking it…

The new video and screen-share capabilities in ChatGPT and Gemini should make rubber-ducking smoother. I feel like I've worn out my computer’s clipboard and alt-tab keys at this stage of the LLM experience.

You may want to try any of the tools that can write to the filesystem so you're at least not copy pasting code from a chat window. CoPilot, Cursor, Aider, Tabnine, etc.

Re: How I program with LLMs

#137

Post by logicchains »

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 test. If you can write unit tests you understand and it passes them all (or visually inspect/test a GUI it generated), you know it's doing well.

Re: How I program with LLMs

#138

Post by fragmede »

roskilli wrote: post #6
justatdotin wrote: post #3

lots of colleauges using copilot or whatever for autocomplete - I just find that annoying. or writing tests - that's ... not so helpful. worst is when a lazy dev takes the generated tests and leaves it at that: usually just a few placeholders that test the happy path but ignore obvious corner cases. (I suppose for API tests that comes down to adding test case parameters) but chatting about a large codebase, I've been…

If you don’t mind me asking: which popular LLM(s) have you been using for this and how are you providing the code base into the context window?

Not OP but Aider provides a repo map to the LLM as context, which consists of the directory tree, filenames, and important symbols in each file. It can use the popular LLMs as well as Ollama.

https://aider.chat/docs/repomap.html

Aider hosts a leaderboard that rates LLMs on performance, including a section on refactoring.

https://aider.chat/docs/leaderboards/refactor.html

Re: How I program with LLMs

#139

Post by AnnKey »

dxuh wrote: post #135

Currently a lot of my work consists of looking at large, (to me) unknown code bases and figuring out how certain things work. I think LLMs are currently very bad at this and it is my understanding that there are problems in increasing context window sizes to multiple millions of tokens, so I wonder if LLMs will ever get good at this.

I would speculate that for learning unknown codebases, fine-tuning might work better than relying on context window size.

Re: How I program with LLMs

#140

Post by pplonski86 »

ignoramous wrote: post #123
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…

I'm in similar situations, I jump between many environments, mainly between Python and Typescript, however, currently testing a new idea of learning algorithm in C++, and I simply don't always remember all syntax. I was very skeptical about LLMs at first. Now, I'm using LLMs daily. I can focus more on thinking rather than searching stackoverflow. Very often I just need simple function, that it is much faster to create with chat.
Post reply on HN