machine-learning
2 posts
Article
Rewriting weights live on 8GB of VRAM
mini-AGI trains a byte-level MoE model from scratch on an 8GB GPU, keeping weights on disk and paging experts in, learning as it reads.
Article
The model kept no receipts
A mathematician presents evidence that OpenAI may have trained its Astra model on his private work on a conjecture it was then credited with solving.