DeepMind Paper: Dream-RSI: Recursive Self-Improvement Through Evolving Worlds

Discussion (3 Comments)Read Original on HackerNews

yanis_t•about 2 hours ago

Would be very glad if anyone explained to me if and why this is revolutionary.

lantry•about 1 hour ago

Here you go:

"Across algorithm engineering, mathematical optimization, and GPU kernel engineering, Dream-RSI achieves competitive or improved discovery quality while substantially reducing discovery cost in several settings."

dgellow•about 1 hour ago

Why would you assume it is revolutionary?

catigula•7 minutes ago

Because “recursive self-improvement” is widely understood, even at labs, as having a non-trivial chance of eradicating human life.

This is like asking why a paper called “I discovered God. This is the specific proof.” is revolutionary. Just tedious levels of incredulity.

WarmWash•about 1 hour ago

Probably isn't by virtue of it being publicly released

cmrdporcupine•about 1 hour ago

Fairly certain all the labs are doing this (RSI) at this point. It's a question of how public their proclamations are about it and how they're positioning PR etc.

Even today's lighter weight models know how to write kernels and optimize them. I've had DeepSeek 4.1 Flash tune the crap out custom CUDA kernels on my own codebase and it was entirely competent at it. And cheap.

The innovation pieces will be in the harnesses to support this. Which I guess is partially what's going on here.

suddenlybananas•about 1 hour ago

It's not really RSI if you are just using the AI as a tool to help make it better. It has to be doing it itself, no? Otherwise self-hosted compilers are RSI.

cmrdporcupine•about 1 hour ago

That's my point about the harness.

DeepMind Paper: Dream-RSI: Recursive Self-Improvement Through Evolving Worlds

⚡ Community Insights

Discussion (3 Comments)Read Original on HackerNews