AI Dynamics

Global AI News Aggregator

About

Training LLMs for Long Context Manipulation Tasks

Oh yes I see. Yes my hope is that it’s something solvable (i like on this topic eg Jina’s work) but we will need to train them more specifically on (long) context manipulation tasks. We’re lacking a bit of open benchmark/evals on this as well (simple manipulation without complex

→ View original post on X — @thom_wolf,