How I program with LLMs
crawshaw.io
How I program with LLMs
1–10 of 342 posts
Re: How I program with LLMs
#2The 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)
Re: How I program with LLMs
#3lots 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 amazed at how helpful it can be.
what software patterns can you see in this repo? how does the implementation compare to others in the organisation? what common features of the pattern are missing?
also, like a linter on steroids, chat can help explore how my project might be refactored to better match the organisation's coding style.
Re: How I program with LLMs
#4I’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, but unlike a code review, it’s not finished code. It probably doesn’t compile, big chunks of it are not quite what you want, it’s not structured into coherent changesets…it’s kind of like you gave the intern the problem and they submitted a bit of a mess. It would be a terrible PR, but it’s a useful intermediate state to take another step from.
It feels like the IDE needs a new mode to deal with this state, and that SCM needs to be involved somehow too. Somehow help the developer guide this somewhat flaky stream of edits and sculpt it into a good changeset.
Re: How I program with LLMs
#5LLMs are, at their core, search tools. Training is indexing and prompting is querying that index. The granularity being at the n-gram rather than the document level is a huge deal though.
Properly using them requires understanding that. And just like we understand every query won’t find what we want, neither will every prompt. Iterative refinement is virtually required for nontrivial cases. Automating that process, like eg cursor agent, is very promising.
Re: How I program with LLMs
#6lots 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?
Re: How I program with LLMs
#7Our 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.
Re: How I program with LLMs
#8The 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)
Exactly, you have to (vaguely) know what you’re looking for and have some basic ideas of what algorithms would work. AI is good at helping with syntax stuff but not really good at thinking.
Re: How I program with LLMs
#9I’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…
Aider commits to git with each command, making it easy to back out changes, and also squash them into discrete chunks later (and reorder them with interactive rebase).
Re: How I program with LLMs
#10Our 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.
The same way responsible enterprise class companies rely on "trust us bro" EULAs for financial systems, customer databases, payroll, and all the other systems it would be very expensive and error prone to build custom for every business.