Recursive LLM prompts

by vlan121on 4/17/2025, 7:46 PMwith 19 comments

by mertleeeon 4/20/2025, 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 ivapeon 4/20/2025, 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 danielblnon 4/20/2025, 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 kordlessagainon 4/20/2025, 11:47 PM

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

by K0balton 4/21/2025, 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_Kon 4/20/2025, 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 mentalgearon 4/22/2025, 8:40 AM

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

by seeknotfindon 4/20/2025, 6:26 PM

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

by NooneAtAll3on 4/20/2025, 8:05 PM

LLM quine when?

by mentalgearon 4/22/2025, 8:40 AM

Should definitely get a date tag.