| ▲ | Yoric 6 days ago | |||||||||||||
> There are experimental AI agents that can patch their own code and explore a tree of possibilities to boost their own performance. However, at the moment they tap out after getting about as good as open source agents, but before they're as good as proprietary agents. Interesting. Do you have links? | ||||||||||||||
| ▲ | torbab 6 days ago | parent [-] | |||||||||||||
Not OP, but the Darwin Godel machine comes to mind: https://arxiv.org/abs/2505.22954 | ||||||||||||||
| ||||||||||||||