On: Dream-RSI: Recursive Self-Improvement through Evolving Worlds

[computably]

Narrow pre-LLM models that spit out content and ad recommendations have never been capable of also suggesting, let alone implementing, self-improvements.

[ctolsen → computably]

The systems that train them do.

[computably → ctolsen]

Not sure if you're trying to be humorous but RSI is when a system improves itself. It's explicit in two out of the three words...