Trying to actually define continual learning
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
- You can’t imitation-learn how to continual-learn — LessWronglesswrong.com
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- The Continual Learning Problemjessylin.com
- What's so hard about continuous learning?seangoedecke.com
- What are the real problems of continual learning?infinitefaculty.substack.com
- Lil'Loglilianweng.github.io
- Continual Learning in Token Space | Lettaletta.com
- augustus odena on X: "I have a bunch of thoughts about continual learning and nothing to do with them (I'm working on something else) so I figured I'd just turn them into a post: First: I think people use "continual learning" to point at a cluster of issues that are related but distinct. I'll list" / Xx.com
- How to Learn Better in the Digital Agegiansegato.com
- Memory Models: Towards Agents That Learnletta.com
- Challenges of governing continually learning AIruntimeverification.blog
- How Might We Learn?andymatuschak.org