Ask HN: What are the most autonomous AI agents you know of?

1 pointFailMore1 comment

Hi all, I'm an engineer and most of my work with AI keeps me fairly closely in the loop - reviewing output or giving permissions. However, it's very clear that with enough permissions / MCPs, the LLM could do its own thing ~indefinitely.

I'm curious if anyone knows of any extremely autonomous AI agents which run in perpetuity or close to that?

Thanks for any answers, thoughts or ideas!

View on HN

> it's very clear that with enough permissions / MCPs, the LLM could do its own thing ~indefinitely.

What exactly is your proof?

I'm not opposed to the idea, but in my experience LLM performance falls through the floor once you run out of input tokens. It seems inevitable that AI will continue writing code until it cannot understand what it's doing anymore.

Reply on news.ycombinator.com