Topic
Continual Learning
2 stories on this topic, newest first.
ResearchExplainer
Agent memory in files: what Anthropic's dreaming experiments show
Anthropic's tests favour stating what memory is for, checking notes against transcripts offline and one writer per page. The wiki gain is narrower.
ResearchExplainer
Why Google wants language models to sleep between tasks
Periodic consolidation offers a different answer to stale knowledge. The important questions are what persists, what changes and whether older capabilities survive.
