i'm convinced all these people with multi-LLM workflows are placebo psyopping themselves
"yeah i have gemini do literature search that i feed to claude for high level design then have gpt implement"
you are not well, seek help
Why does deep learning generalize? What does weight decay really do? Can algorithmic information theory address these questions?
In my latest preprint, I give a proof that the minimum neural weight norm matches the minimum program length (aka Kolmogorov Complexity), up to a logarithmic factor. In other words, the neural network with the smallest possible weight norm (that fits the data) must encode the shortest program (that fits the data).
The result only holds for fixed-precision neural nets: infinite precision nets can store infinite information with finite (small) weights.
https://t.co/eMZIGQDf2f
@xurbanxcowboyx@skulllllkid@blancmontagnard Ok there’s some disconnect here. FAANG is automatic, many bad candidates. Not kiss of death (obviously). Not a passport either. Facebook seems especially low quality
god what a beautiful objective. i wonder how general you can push this. best non-distillation answer ive seen for knowledge acq during RL, feels bitter-pilled in a way that most self-teaching methods aren’t.
Guys, stop pestering Mech Interp researchers about causality please! It's this inexplicable obsession with causality that made us lose beautiful sciences like Astrology, Palmistry and Phrenology! 😡