Inspired by human dreaming as a memory reconsolidation process, Anthropic has its AI agents use downtime to "dream." During this background process, the agent reviews its memories, identifies and prunes contradictions, and cleans up the information to improve the coherence and utility of its long-term memory.

Future AI expressivity won't come from adding more identical layers, but from 'nesting' levels with different update frequencies. This allows some parts of the system to adapt rapidly (like working memory) while others preserve core knowledge (long-term memory), mimicking human cognition.

Karpathy identifies a key missing piece for continual learning in AI: an equivalent to sleep. Humans seem to use sleep to distill the day's experiences (their "context window") into the compressed weights of the brain. LLMs lack this distillation phase, forcing them to restart from a fixed state in every new session.

A key function of dreaming is to explore weak associations between new and old memories (a process called NEXTUP). The brain weaves these connections into a narrative, and your emotional reaction within the dream serves as the evaluation mechanism to decide if the new association is valuable and worth strengthening.

The 'dreaming' phase in continual learning isn't just for memory consolidation. It serves to actively find connections between concepts that seem unrelated based on recent experiences. This process allows the model to form new, higher-level abstractions and insights, mirroring a key function of human dreaming.

To manage context effectively, an AI OS can run a nightly routine ('dreaming') that reviews daily memory files, compresses key information, and saves it into a long-term memory file. This process mimics human memory consolidation, preventing context loss over time.

A new OpenClaw feature called "dreaming" allows the AI agent to process information and consolidate memories overnight while inactive. This concept, borrowed from human neuroscience, aims to improve the agent's long-term learning and performance without requiring active user input, mimicking how humans process experiences during sleep.

Claude's "Dreams" feature is not automatic learning but an explicit API call to review past sessions and synthesize memories. This design gives developers direct control over when and what an agent learns, transforming memory management from a black box into a deliberate, auditable action.

A genuinely continual learner doesn't have separate training and testing phases. Instead, its life is a continuous process divided into two modes: an 'active' phase of interacting with new data and an 'offline' sleep phase for memory consolidation and self-improvement.