Even with vast training data, current AI models are far less sample-efficient than humans. This limits their ability to adapt and learn new skills on the fly. They resemble a perpetual new hire who can access information but lacks the deep, instinctual learning that comes from experience and weight updates.

Implementing effective long-term memory for AI agents is a major unsolved problem. The difficulty is not in storing information, but in automatically generating useful memories from interactions and accurately retrieving the correct, context-specific memory without cluttering the prompt with irrelevant information.

Solving key AI weaknesses like continual learning or robust reasoning isn't just a matter of bigger models or more data. Shane Legg argues it requires fundamental algorithmic and architectural changes, such as building new processes for integrating information over time, akin to an episodic memory.

AI agents need a multi-faceted memory architecture inspired by human cognition. This includes episodic (time-stamped events), semantic (world knowledge), procedural (workflows and skills), and working memory (immediate context window).

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.

Retrieval-Augmented Generation (RAG) is just one component of agent memory. A robust system must also handle dynamic operations like updating information, consolidating knowledge, resolving conflicts, and strategically forgetting obsolete data.

The idea of separating "fact learning" from "skill learning" is a false dichotomy. Models need a base of internalized facts to reason effectively. The key is developing intelligence to compress what's important and discard what isn't, much like lossy human memory.

The "memory" feature in today's LLMs is a convenience that saves users from re-pasting context. It is far from human memory, which abstracts concepts and builds pattern recognition. The true unlock will be when AI develops intuitive judgment from past "experiences" and data, a much longer-term challenge.

Continuously training a model on private data internalizes concepts, reducing the need for massive context windows and system prompts. This dramatically cuts token consumption for inference compared to RAG-based approaches that re-read documents repeatedly.