TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Recursive LLM prompts

81 pointsby vlan121about 1 month ago

10 comments

mertleeeabout 1 month ago
&quot;Foundational AI companies love this one trick&quot;<p>It&#x27;s part of why they love agents and tools like cursor -&gt; turns a problem that could&#x27;ve been one prompt and a few hundred tokens into dozens of prompts and thousands of tokens ;)
评论 #43746294 未加载
ivapeabout 1 month ago
<i>The bigger picture goal here is to explore using prompts to generate new prompts</i><p>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 &quot;how can I get the LLM to generate a whole book&quot;, well, just like this. If it can keep prompting itself to ask &quot;what would chapter N be?&quot; until &quot;THE END&quot;, then you get your book.
评论 #43746414 未加载
danielblnabout 1 month ago
The last commit is from April 2023, should this post maybe have a (2023) tag? Two years is eons in this space.
评论 #43746733 未加载
评论 #43771952 未加载
评论 #43747779 未加载
kordlessagainabout 1 month ago
I love this! My take on it for MCP: <a href="https:&#x2F;&#x2F;github.com&#x2F;kordless&#x2F;EvolveMCP">https:&#x2F;&#x2F;github.com&#x2F;kordless&#x2F;EvolveMCP</a>
K0baltabout 1 month ago
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.<p>Still clever.
James_Kabout 1 month ago
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.
mentalgear29 days ago
Trying to save state in a non-deterministic system, not the best idea. Those things need to be externalised.
seeknotfindabout 1 month ago
Excellent fun. Now just to create a prompt to show iterated LLMs are turing complete.
评论 #43747399 未加载
NooneAtAll3about 1 month ago
LLM quine when?
评论 #43746676 未加载
mentalgear29 days ago
Should definitely get a date tag.
评论 #43771936 未加载