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

51–60 of 342 posts

Re: How I program with LLMs

#51

Post by AlotOfReading »

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…

It's interesting that you find it useful for optimization. I've found that they're barely capable of anything more than shallow optimization in my stuff without significant direction.

What I find useful is that I can keep thinking at one abstraction level without hopping back and forth between algorithm and codegen. The chat is also a written artifact I can use the faster language parts of my brain on instead of the slower abstract thought parts.

Re: How I program with LLMs

#52

Post by dewitt »

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 old idea I had of a language where all you wrote was function signatures and high-level control flow, and maybe some conformance tests around them. The language was designed around filling in the implementations for you. 20 years ago that would have been from a live online database, with implementations vying for popularity on the basis of speed or correctness. Nowadays LLMs would generate most of it on the fly, presumably.

Most ideas are unoriginal, so I wouldn't be surprised if this has been tried already.

Re: How I program with LLMs

#53

Post by Kostchei »

pama wrote: post #15
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.

Your company could locally host LLMs; you wont get chatGPT or Claude quality, but you can get something that would have been SOTA a year ago. You can vet the public inference codebases (they are only of moderate complexity), and you control your own firewalls.

You can get standalone/isolated versions of chatGPT, if your org is large enough, in partnership with OpenAI. And others. They run on the same infra but in accounts you set up, cost the same, but you have visibility on the compute, and control of data exfil - ie is there is none.

Re: How I program with LLMs

#54

Post by tptacek »

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…

There's an art to cost-effectively coaxing useful answers (useful drafts of code) from an LLM, and there's an art to noticing the most productive questions to put to that process. It's a totally different way of programming than having an LLM looking over your shoulder while you direct, function by function, type by type, the code you're designing.

If you feel like you're wasting your time, my bet is that you're either picking problems where there isn't enough value to negotiate with the LLM, or your expectations are too high. Crawshaw mentions this in his post: a lot of the value of this chat-driven style is that it very quickly gets you unstuck on a problem. Once you get to that point, you take over! You don't convince the LLM to build the final version you actually commit to your branch.

Generating unit test cases --- in particular, generating unit test cases that reconcile against unsophisticated, brute-force, easily-validated reference implementations of algorithms --- are a perfect example of where that cost/benefit can come out nicely.

Re: How I program with LLMs

#55

Post by tptacek »

m3kw9 wrote: post #20
bangaladore wrote: post #19

The killer feature about LLMs with programming in my opinion is autocomplete (the simple copilot feature). I can probably be 2-3x more productive as I'm not typing (or thinking much). It does a fairly good job pulling in nearby context to help it. And that's even without a language server. Using it to generate blocks of code in a chat like manner in my opinion just never works well enough in the domains I use it on.…

The autocomplete is mostly a nusance and maybe low percentage of the time it does right.

Yeah, I don't like it either. I think it speaks to the mindset difference Crawshaw is talking about here. When I'm writing code, I don't want things getting in my way. I have a plan. I'm actually pretty Zen about all the typing. It's part of my flow-state. But when I'm exploring code in a dialog with a chatbot, I'm happy for the help.

Re: How I program with LLMs

#56

Post by sdesol »

Scene_Cast2 wrote: post #26
sdesol wrote: post #21

Earlier quoted context omitted.

> LLMs are, at their core, search tools. This is the wrong take. Search tools are deterministic unless you purposely inject random weights into the ranking. With search tools, the same search query will always yield the same search result, provided they are designed too and/or the underlying data has not changed. With LLMs, I can ask the exact same question and get a different response, even if the data has not chang…

The randomness comes from sampling. With local LLMs, you can fix the random seed, or even disable sampling all together - both will get you determinism. I agree that LLMs are not search tools, but for very different reasons.

Thanks for the info on local LLMs. Based on my chats with multiple LLMs, the biggest issue appears to be hardware.

Non-deterministic hardware: All LLMs mentioned that modern computing hardware, such as GPUs or TPUs, can introduce non-determinism due to factors like parallel processing, caching, or numerical instability. This can make it challenging to achieve determinism, even with fixed random seeds or deterministic algorithms.

You can find the summary of my chats https://beta.gitsense.com/?chat=1c3e69f9-7b8b-48a3-8b99-bb1b.... If you scroll to the top and click on the "Conversation" link in the first message, you can read the individual responses.

Re: How I program with LLMs

#57

Post by chii »

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.

Re: How I program with LLMs

#58

Post by BBosco »

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.

The vast majority of fortune 500’s have legal frameworks up for dealing with internal AI use already because the reality is employees are going to use it regardless of internal policy. Assuming every employee will act in good faith just because a blanket AI ban is in place is extremely optimistic at best, and isn’t a good substitute for actual understanding.

Re: How I program with LLMs

#59

Post by agentultra »

It seems nice for small projects but I wouldn’t use it for anything serious that I want to maintain long term.

I would write the tests first and foremost: they are the specification. They’re for future me and other maintainers to understand and I wouldn’t want them to be generated: write them with the intention of explaining the module or system to another person. If the code isn’t that important I’ll write unit tests. If I need better assurances I’ll write property tests at a minimum.

If I’m working on concurrent or parallel code or I’m working on designing a distributed system, it’s gotta be a model checker. I’ve verified enough code to know that even a brilliant human cannot find 1-in-a-million programming errors that surface in systems processing millions of transactions a minute. We’re not wired that way. Fortunately we have formal methods. Maths is an excellent language for specifying problems and managing complexity. Induction, category theory, all awesome stuff.

Most importantly though… you have to write the stuff and read it and interact with it to be able to keep it in your head. Programming is theory-building as Naur said.

Personally I just don’t care to read a bunch of code and play, “spot the error;” a game that’s rigged for me to be bad at. It’s much more my speed to write code that obviously has no errors in it because I’ve thought the problem through. Although I struggle with this at times. The struggle is an important part of the process for acquiring new knowledge.

Though I do look forward to algorithms that can find proofs of trivial theorems for me. That would be nice to hand off… although simp does a lot of work like that already. ;)

Re: How I program with LLMs

#60

Post by sibeliuss »

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…

My technique is to feed it a series of intro questions that prepare it for the final task. Chat the thing into a proper comfort level, and then from there, with the context at hand, ask to help solve the real problem. Def feels like a new kind of programming model because its still very programming-esque.
Post reply on HN