Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

news.ycombinator.com

Post reply on HN
Print view View original

231–240 of 247 posts

Re: Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

#231

Post by rramadass »

aard wrote: post #227
rramadass wrote: post #225

Earlier quoted context omitted.

Nice. There have been some similar activities on this front. In case you didn't already know of them; Literate Programming in the Age of LLMs - https://news.ycombinator.com/item?id=48691666 Natural Language Outlines for Code: Literate Programming in the LLM Era (inspired by LP) - https://dl.acm.org/doi/10.1145/3696630.3728541 Visual Programming + Literate Programming: A Better Way to Build Business Logic With AI - ht…

This is wonderful, thanks! I was unaware of these!

You might also find my previous comment chains useful - https://news.ycombinator.com/item?id=48431591 https://news.ycombinator.com/item?id=48618662 and https://news.ycombinator.com/item?id=48264680

With AI agents we need some way to specify requirements, trace that they are met through the generated code and verify them against the requirements. All with the ability to generate documentation and facilitating understanding. Changes made to the specification should update code and vice-versa auto-magically. That is the holy grail of "Round-Trip Engineering".

Re: Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

#232

Post by kpatucha »

Barely anyone here touched on your idea that tab completion is great use of AI. On paper I like the idea of tab completion - I'm closer to the code, I'm doing, not waiting, I have more control. However, I'm not programmer building some complicated application - I'm data scientist writing short fragments of code to analyze data, train models and serve them. So maybe I don't see a big picture of code development.

Having said that, I cannot internalize how tab completion fits into my workflow - what are the benefits compared to IntelliSense. So far I've used LLMs as glorified search engines or to better understand some concepts.

In order to get a feel for tab completion I've installed continue.dev VS Code extension and connected it to local model. I don't know if there are better free alternatives (I hope so, since continue.dev project was killed recently and will not be ... continued)

Re: Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

#236

Post by mohit17mor »

I am exploring the idea of event driven agents to reduce human inputs as much as possible, basically I should be able to just create tasks and the agents just keep picking them up as they get free. Also, trying to extend it to chaining the agents so that it can create an end to end workflow. For coding it might look something like this: User creates a task -> coder picks it up -> reviewer agent -> (coder/reviewer back and forth upto 4-5 turns) -> tester agent -> finally wait for user to merge the code or not.

This has nothing to do with agent harness as such, its more like treating agents as instantiable objects and adding control plane on top of them to get the work done.

Re: Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

#237

Post by deterministic »

satvikpendem wrote: post #119

As Boris said, you shouldn't be manually prompting anymore but asking the AI to prompt itself, in the form of workflows. I usually have 3 to 5 different sessions running at once all autonomously.

Not verifying the generated code is a really bad idea.

Re: Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

#238

Post by uday_singlr »

Haven't experienced flow state in a while, since CC became my default IDE :)

I built my version of a meta harness that guides claude and codex in a code => review loop. I typically brainstorm a task and dispatch it. The actual coding and review by the LLMs is done in a sandboxed Incus container. A WIP https://github.com/standardapplied/sail

Post reply on HN