3 stories tagged continual-learning, newest first.
141 points by geoffbp | 72 comments
Anthropic engineering post describing components of AI agent memory—notes, representations, injected context, and 'dreaming' consolidation—with evaluations on CL-Bench and Pokémon Red.
101 points by handfuloflight | 10 comments
arXiv paper introducing Memorilla, a system that compresses document collections into query-dependent memory tokens in the input embedding space of frozen LLMs.
227 points by acossta | 30 comments
Google Research blog post introducing a sleep framework that lets LLMs consolidate short-term context into long-term parameters and self-improve via 'dreaming' during continual learning.