New preprint shows how ideas from distributed computing can be used to understand the performance of teams of language model agents on different kinds of tasks
Current AI models are trained on human behavior -- the words we produce. New preprint explores the idea that we might be able to address some of the gaps in these systems by training on the latent variables behind that behavior: human cognition.
We will be releasing edited versions of the interviews in a podcast format over the next few months.
The book takes the 19th century idea that there are Laws of Thought just as there are Laws of Nature — mathematical principles that explain how minds work — and traces that idea through the Cognitive Revolution of the 20th century to a 21st century perspective on what those Laws might be.
I'm excited to announce that I had my first (co-authored) book published today! "The Rational Use of Cognitive Resources" with Falk Lieder and Tom Griffiths (@cocoscilab.bsky.social ). You can read it for free! (see thread)
