Anthropic finds selective memory beats exhaustive storage in AI agents
anthropic tested claude's memory across sessions, finding selective note-taking outperforms exhaustive archives, and a process called 'dreaming' corrects faulty notes. this improves agent performance.
anthropic tested claude's ability to store and retrieve information across sessions. claude wrote notes to a folder, but exhaustive note-taking overwhelmed the model with outdated data. selective note-taking, focusing on strategies and rules, worked better. anthropic also developed 'dreaming', a process where claude reviews earlier session transcripts during idle periods to correct faulty notes and build structured knowledge collections. this approach improved claude's performance in tasks like playing pokémon.