flâneur

Trying to actually define continual learning

charlesponeill.com · 2,236 words · saved by 1 readers

Every AI agent today is an amnesiac intern. You can teach it an astonishing amount inside one context window. Then the context window ends, a new intern arrives, and all it has are the notes the previous one left behind. The notes can get better but the intern does not. This is why continual learning feels like the holy grail of AI research. We have a recipe for creating intelligent machines. Wha

Every AI agent today is an amnesiac intern. You can teach it an astonishing amount inside one context window. Then the context window ends, a new intern arrives, and all it has are the notes the previous one left behind. The notes can get better but the intern does not. This is why continual learning feels like the holy grail of AI research. We have a recipe for creating intelligent machines. What we do not really have is a way for one of those machines to keep learning from experience over long time horizons. To be clear, I mean a narrower problem than the one the big labs usually care…

related reading