Anthropic found Claude Sonnet 3.7 getting stuck managing its own memory while playing Pokémon.
“Over the next 17 steps, it created six files, deleted nine others, and took no actions in the game itself.”
In one run, it wrote 413 files and earned one badge. A stronger model kept just nine files and earned four badges in its run.
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time.