miniblog.

The word "agent" is so overloaded in the AI space. Sometimes it means a sophisticated interaction system, but other times it just means API. I think it's partly a sign of how new the space is. We don't have consensus on the best way to use these systems yet.

@tristanC That's an option! There's often cases where you know what the user wanted though, so you can provide a sensible AST that the toolchain can handle. For example, a malformed string literal can still be parsed a string so type checking etc can be helpful.

I've been experimenting with an 'evaluate up to cursor' mode for my PL project. I love evaluating self-contained snippets in Lisp, this generalises the idea. The interpreter remembers the arguments when you run tests, then can re-use them when you say 'eval up to here'. What do you think?