AI just learned to fine-tune itself between questions. MIT introduces SEAL, a framework enabling LLMs to self-edit and update their weights via reinforcement learning, all by itself. LLMs consume whatever data they are given, so they stay frozen after pretraining. SEAL teaches https://t.co/rQVPWoSp2W
— Rohan Paul (@rohanpaul_ai) Jun 16, 2025
from Twitter https://twitter.com/rohanpaul_ai
June 16, 2025 at 08:50PM
via IFTTT
No comments:
Post a Comment