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

11–20 of 342 posts

Re: How I program with LLMs

#11

Post by itsgrimetime »

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)

IMO this is a bad take. I use LLMs for things I don’t know how to do myself all the time. Now, I wouldn’t use one to write some new crypto functions because the risk associated with getting it wrong is huge, but if I need to write something like a wrapper around some cloud provider SDK that I’m unfamiliar with, it gets me 90% of the way there. It also is way more likely to know at least _some_ of the best practices where I’ll likely know none. Even for more complex things getting some working hello world examples from an LLM gives me way more threads to pull on and research than web searching ever has.

Re: How I program with LLMs

#12

Post by photon_collider »

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)

"Trust but verify" is still useful especially when you ask LLMs to do stuff you don't know. I've used LLMs to help me get started on tasks where I wasn't even sure of what a solution was. I would then inspect the code and review any relevant documentation to see if the proposed solution would work. This has been time consuming but I've learned a lot regardless.

Re: How I program with LLMs

#13

Post by Retr0id »

itsgrimetime wrote: post #11
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)

IMO this is a bad take. I use LLMs for things I don’t know how to do myself all the time. Now, I wouldn’t use one to write some new crypto functions because the risk associated with getting it wrong is huge, but if I need to write something like a wrapper around some cloud provider SDK that I’m unfamiliar with, it gets me 90% of the way there. It also is way more likely to know at least _some_ of the best practices w…

> if I need to write something like a wrapper around some cloud provider SDK that I’m unfamiliar with

But "writing a wrapper" is (presumably) a process you're familiar with, you can tell if it's going off the rails.

Re: How I program with LLMs

#14

Post by IanCal »

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)

That seems like a wild restriction.

You can give them more latitude for things you know how to check.

I didn't know how to setup the right gnarly typescript generic type to solve my problem but I could easily verify it's correct.

Re: How I program with LLMs

#15

Post by pama »

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.

Re: How I program with LLMs

#17

Post by IanCal »

User23 wrote: post #5

LLMs 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, l…

Half of the problems are people treating them as searchers when they aren't. They're absolutely not ngram indexes of existing data, either.

Re: How I program with LLMs

#18

Post by mvdtnz »

User23 wrote: post #5

LLMs 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, l…

I'm losing track of the number of different things the Hacker News commenters claim LLMs are "at their core".

Re: How I program with LLMs

#19

Post by bangaladore »

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. I'll try to get it to generate something and then realize when I get some functional result I could've done it faster and more effectively.

Funny enough, other commenters here hate autocomplete but love chat.

Re: How I program with LLMs

#20

Post by m3kw9 »

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.
Post reply on HN