from Hacker News

Recursive LLM prompts

by vlan121 on 4/17/25, 7:46 PM with 19 comments

• by mertleee on 4/20/25, 6:36 PM

  "Foundational AI companies love this one trick"

  It's part of why they love agents and tools like cursor -> turns a problem that could've been one prompt and a few hundred tokens into dozens of prompts and thousands of tokens ;)

• by ivape on 4/20/25, 6:34 PM

  The bigger picture goal here is to explore using prompts to generate new prompts

  I see this as the same as a reasoning loop. This is the approach I use to quickly code up pseudo reasoning loops on local projects. Someone had asked in another thread "how can I get the LLM to generate a whole book", well, just like this. If it can keep prompting itself to ask "what would chapter N be?" until "THE END", then you get your book.

• by danielbln on 4/20/25, 8:23 PM

  The last commit is from April 2023, should this post maybe have a (2023) tag? Two years is eons in this space.

• by kordlessagain on 4/20/25, 11:47 PM

  I love this! My take on it for MCP: https://github.com/kordless/EvolveMCP

• by K0balt on 4/21/25, 4:43 AM

  This is kind of like a self generating agentic context.. cool. I think regular agents, especially adversarial agents, are easier to get focused on most types of problems though.

  Still clever.

• by James_K on 4/20/25, 9:35 PM

  I feel that often getting LLMs to do things like mathematical problems or citation is much harder than simply writing software to achieve that same task.

• by mentalgear on 4/22/25, 8:40 AM

  Trying to save state in a non-deterministic system, not the best idea. Those things need to be externalised.

• by seeknotfind on 4/20/25, 6:26 PM

  Excellent fun. Now just to create a prompt to show iterated LLMs are turing complete.

• by NooneAtAll3 on 4/20/25, 8:05 PM

  LLM quine when?

• by mentalgear on 4/22/25, 8:40 AM

  Should definitely get a date tag.