How does Searles emphasis on direction of fit for different intentional states mesh with the Bayesian brain idea of predictive processing and action and belief/perception being the same kind of process just run in different directions. See SSC on error correction I guess?
Chip Huyen’s 8,000 word practical guide to building useful LLM-driven workflows that take advantage of tools.
Chip starts by providing a definition of “agents” to be used in the piece - in this case it’s LLM systems that plan an approach and then run tools in a loop until a goal is achieved. I like how she ties it back to the classic Norvig “thermostat” model - where an agent is “anything that can perceive its environment and act upon that environment” - by classifying tools as read-only actions (sensors) and write actions (actuators).