Very interesting read. I build self evolving ai agents for my own use with Claude Code, and although the paper seems to be slightly behind where we are today, there are many ideas I hadn't considered I should explore more.

Very much appreciate the submission.

▲

drwere 4 days ago | parent | next [-]

Have you tried letting it completely evolve itself without direction as to what it becomes? I keep waiting to hear about someone trying that, but I think most are too scared to try it, although it really can’t be any more dangerous than what’s already happened and continues to happen in the world.

	▲	AndyNemmity 4 days ago \| parent [-]
		Yes, I've literally made an anarchist collective software engineering firm where all the agents make all the decisions.

▲

celurian92 4 days ago | parent | prev [-]

would love to know how? do you have any blogs or tutorials that I can follow to get started on making self evolving ai agents?

▲

AndyNemmity 4 days ago | parent [-]

I don't enjoy making blogs or tutorials. I just keep building new things. It's a lot of fun right now.

▲

celurian92 3 days ago | parent | next [-]

I was thinking like your source of learning, it can be books, tutorial etc. I am not asking for blogs or tutorials made by you

	▲	AndyNemmity 2 days ago \| parent [-]
		My source of learning is trying weird ideas. I wanted to learn about agents and how they worked, so I built an autonomous consensus based set of AI agents with no human intervention to build a software collective. In that process, I learned interesting things about how agents work. Then I used those ideas, to build agents for other tasks, and I have been working on improving those with other weird ideas. Through these process, I develop opinions about how they work. They may be incorrect, but it gives me a certain kind of insight into them, and how to adjust them.

▲

highd 4 days ago | parent | prev [-]

If you released any of the software you are using to do this I would find it extremely interesting!