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

101–110 of 342 posts

Re: How I program with LLMs

#101

Post by zkry »

singpolyma3 wrote: post #42

It seems like everything I see about success using LLMs for this kind of work is for greenfield. What about three weeks later when the job changes to maintenance and interation on something that's already working? Are people applying LLMs to that space?

Logically this makes sense: every model has a context size and complexity capacity where it will no longer be able to function properly. Any usage of said model will accelerate the approach to this limit. Once the limit is reached, the LLM is no longer as helpful as it was.

I work on full blown legacy apps and needless to say I don't even bother with LLMs when working on these most of the time.

Re: How I program with LLMs

#102

Post by justinl33 »

I've maintained several SDKs, and the 'cover everything' approach leads to nightmare dependency trees and documentation bloat. imo, the LLM paradigm shifts this even further - why maintain a massive SDK when users can generate precisely what they need? This could fundamentally change how we think about API distribution.

Re: How I program with LLMs

#103

Post by wruza »

Guthur wrote: post #93
sunaookami wrote: post #85

Earlier quoted context omitted.

>I've been in the industry for nearly 25 years and have heard auto complete throughout but not once have I heard fill in the middle Then you need to look harder. FiM is a common approach for code generation LLMs. https://openai.com/index/efficient-training-of-language-mode... https://arxiv.org/abs/2207.14255 This was before ChatGPT's release btw.

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.

Re: How I program with LLMs

#104

Post by EagnaIonat »

brabel wrote: post #97
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…

I am not a genius but have a couple of decades experience and finally started using LLMs in anger in the last few weeks. I have to admit that when my free quota from GitHub Copilot ran out (I had already run out of Jetbrains AI as well!! Our company will start paying for some service as the trials have been very successful), I had a slight bad feeling as my experience was very similar to OP: it's really useful to get…

Have you tried using Ollama? You can download and run an LLM locally on your machine.

You can also pick the right model for the right need and it's free.

Re: How I program with LLMs

#105

Post by golergka »

I have written a small fullstack app over the holidays, mostly with LLMs, to see how far would they get me. Turns out, they can easily write 90% of the code, but you still need to review everything, make the main architectural decisions and debug stuff when AI cant solve the bug after 2-3 iterations. I get a huge productivity boost and at the same time am not afraid that they will replace me. At least not yet.

Can't recommend aider enough. I've tried many different coding tools, but they all seem like a leaky abstraction over LLMs medium of sequential text generation. Aider, on the other hand, leans into it in the best possible way.

Re: How I program with LLMs

#106

Post by lysecret »

greenyouse wrote: post #95
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 approach sounds similar to the Idris programming language with Type Driven Development. It starts by planning out the program structure with types and function signatures. Then the function implementation (aka holes) can be filled in after the function signatures and types are set. I feel like this is a great approach for LLM assisted programming because things like types, function signatures, pre/post condition…

100% this is what I do in python too!

Re: How I program with LLMs

#108

Post by golergka »

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.

What's the realistic attack scenario? Will Sam Altman steal your company's code? Or will next version of GPT learn on your secret sauce algorithms and then your competitors will get them when they generate code for their tasks and your company loses its competitive advantage?

I'm actually sure that there are companies for which these scenarios are very real. But I don't think there's a lot of them. Most of the code our industry works on has very little value outside of context of particular product and company.

Re: How I program with LLMs

#109

Post by golergka »

fragmede wrote: post #9
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…

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).

Automatically runs linter and tests on every edit and forwards failures back to LLM as well.

Re: How I program with LLMs

#110

Post by devjab »

brabel wrote: post #97
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…

I am not a genius but have a couple of decades experience and finally started using LLMs in anger in the last few weeks. I have to admit that when my free quota from GitHub Copilot ran out (I had already run out of Jetbrains AI as well!! Our company will start paying for some service as the trials have been very successful), I had a slight bad feeling as my experience was very similar to OP: it's really useful to get…

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 based on trusting strangers on the internet that it never really made much sense once I started knowing what I was doing. I sort of view LLM's in a similar manner. Why would you go to them rather than the actual documentation? I realize this might sound arrogant or rude, and I really hope you believe me when I say that I don't mean it like this. The reason I'm curious is because we're really struggling getting junior developers to not look, everywhere, but the documentation first. Which means they often actually don't know how what they build works. Which can be an issue when they load every object of a list into memory isntead of using a generator...

As far as using LLMs in anger I would really advice anyone to use them. GitHub copilot hasn't been very useful for me personally, but I get a lot of value out of running my thought process by a LLM. I think better when I "think out loud" and that is obviously challenging when everyone is busy. Running my ideas by an LLM helps me process them in a similar (if not better) fashion, often it won't even really matter what the LLM conjures up because simply describing what I want to do often gives me new ideas, like "thinking out loud".

As far as coding goes. I find it extremely useful to have LLMs write cli scripts to auto-generate code. The code the LLM will produce is going to be absolute shite, but that doesn't matter if the output is perfectly fine. It's reduced my personal reliance on third party tools by quite a lot. Because why would I need a code generator for something (and in that process trust a bunch of 3rd party libraries) when I can have a LLM write a similar tool in half an hour?

Post reply on HN