Live data from Hacker News

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

news.ycombinator.com

221–230 of 247 posts

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

#224

That's how I code nowadays: 1. Start a session. 2. Grill my requirements. 3. Write an ADR, then either start implementing or separate into pieces. 4. Review the code on pyor.review, compared to Github, Pyor allows me to categorize the files and changes then review the important stuff and skim the noise it identifies. 5. Since I can do local reviews with Pyor, I can do that with Claude and feed back my comments to be…

(user othmanosx owns pyor) whats the catch on pyor, how is it free?

it's a wrapper around GitHub APIs. Github is still the BE, Pyor is only the better UI

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

#225
post #180

I've been experimenting with making AI generate literate code. The goal is to have the AI produce a bunch of prose alongside the code. A lot of context for the purpose and design of what you are doing usually gets thrown away, but with literate programming you can save it. And this way I can have some hope of understanding the code being created. I've liked it so far. I am using a literate programming project I built…

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 - https://www.leapter.com/ai-verification-problem/

Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects - https://arxiv.org/abs/2502.17441

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

#226

Earlier quoted context omitted.

It hits the exact same endorphin system as “one more turn” style games like Civ. You can manage a few cities and keep them healthy, but the rest of your empire eventually regresses into a set of chores. Any time you encounter one of your zero growth cities you just queue some thoughtless production automation to keep it out of your “next turn” cycle as long as possible.

Yeah, I see this as a design flaw in Civ. Better to limit the player's moves per turn to keep things moving. There's a game called "Ozymandius" that I quite like, or for a simple online game try Compact Conflict: https://wasyl.eu/games/compact-conflict/play.html Hopefully the LLM's will get fast enough so we won't need to multitask, or least we can juggle fewer tasks.

Yeah I've used Opus fast mode a few times and it's incredible for staying in a flow state.

But it is crazy expensive so, not a feasible daily driver yet.

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

#227
post #180

I've been experimenting with making AI generate literate code. The goal is to have the AI produce a bunch of prose alongside the code. A lot of context for the purpose and design of what you are doing usually gets thrown away, but with literate programming you can save it. And this way I can have some hope of understanding the code being created. I've liked it so far. I am using a literate programming project I built…

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!

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

#230
post #6

Related question: are there any close-to-gpt5.5/opus-level good autocompletion models?

when it comes to autocomplete, the harness matters more than the model

I have stopped autocompletions. Found easier to just prompt and get it done
Post reply on HN