[pests]

Go and Chess still has rules that are hard coded which at least gives a framework to optimize in. What rules do you give an LLM?

[drdeca]

Some sort of "generate descriptions of novel tasks including ways to evaluate performance at those tasks, evaluate quality of the generated tasks+evaluation-metrics, split tasks into subtasks, estimate difficulty of tasks in a way that is is judged on how it compares to a combined estimated difficulty of generated subtasks and to actual success rate and quality" sort of deal?

[spangry]

Physics.

[faceplanted]

I'm skeptical of the idea that anything is going to derive intelligence from the bottom up, but I'll be super impressed if that's how it goes.

[spangry]

Why not? We started off as single celled organisms and look at where we are now.