Recursive Self-Improvement

Computer, load up celery man.
Can AI build AI? Yes, and it already is. Sort of. I showcase the ability of AI agents like claude code to perform AI research, to build and optimize machine learning algorithms. I put various state-of-the-art LLMs like claude Mythos/Fable into an endless recursive research loop and have them build a neural network that learns the shape of the mandelbrot set. It is inspired by Andrej Karpathy’s autoresearch. While we watch this loop, I express my thoughts on the concept of recursive self improvement, arguing that it is possible, hard, and dangerous.
Sorry for the bitrate issues.

Fractalsearch repo:
Neural Mandelbrot repo:

~SUPPORT ME~
Learn to code faster with Scrimba! (saves you 20% and support me):
Patreon:
Twitter:
Bluesky:

~SOURCES~
Autoresearch:
Mandelbrot Zoom:
Celery Man:
Karpathy’s Youtube:
Self-building Cranes:
Darwin-Godel Machine:
Hashgrid Paper:
Anthropic’s RSI Article:
Fable System Card:

My Music Guy:

“Equatorial Complex”
Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 3.0

~TIMESTAMPS~
(0:00) Recursive Self Improvement
(3:14) fractalsearch
(9:56) RSI is Possible
(15:03) RSI is Hard
(21:52) RSI is Dangerous
(26:03) Results
(28:28) Cost
(29:29) Takeoff

source