I think the bitter lesson has an answer to that question. The best AI language is whichever one has the largest corpus of high quality training data. Perhaps new language designers will come up with new ways to create large, high quality corpi in the future, but for the foreseeable future it looks like the big incumbents have an unassailable advantage.

Smalltalk offers several excellent features for LLM agents:

- Very small methods that function as standalone compilation units, enabling extremely fast compilation.

- Built-in, fast, and effective code browsing capabilities (e.g., listing senders, implementors, and instance variable users...). This makes it easy for the agent to extract only the required context from the system.

- Powerful runtime reflectivity and easily accessible debugging capabilities.

- A simple grammar with a more natural, language-like feel compared to Lisp.

- Natural sandboxing

I'm working on what I hope is an AI-first language now, but I'm taking the opposite approach: something like Swift/DartTypeScript with plenty of high level constructs that compactly describe intent.

I'm focusing on very high-quality feedback from the compiler, and sandboxing via WASM to be able to safely iterate without human intervention - which Hoot has as well.

LLM's are mainly trained on English natural language text, so you'll want a language that looks as much as possible like English. COBOL is it, then.