Episode 17: Andrew Lampinen, DeepMind, on symbolic behavior, mental time travel, and insights from psychology
Generally Intelligent
00:00
Is There a Way to Improve Machine Learning?
Anse po i look at interesting articles in the journal behavior in brain sciences. One article is about generalizability issues in psychology, which i think it's a great article. Anse po I was more sceptical about what you could learn from language alone before recent large language model stuff. And i still think it's necessary to get some kinds of things, but i think i've revised my belief about what kinds of things.
Transcript
Play full episode
