Given that the most important feature for agent performance is the popularity of the language, ie, the amount of training data, (https://danluu.com/pl-tokens/), why would you cause problems for yourself by using Lisp rather than Python/Javascript if you care mainly about results fast, or C/C++/Rust if you care about performance too?

This is an interesting idea. I was thinking about something similar in Smalltalk or Erlang the other day. Mostly building on the actor/object+mailbox concept.

I didn’t actually do anything with that idea yet but may look at the idea in Elixir this weekend.

Amusingly, I started building something very similar in Jolt today :) https://github.com/yogthos/samizdat/