Simon Wardley You probably would need agents + rag for more complicated mapping, agents would need to discuss between each other too before proposing the final result, I think there's too much hype but we will get there.

I am not taking community feedback? Haha

LLM-bros are not my community

I care about communities harmed by AI hype, including marginalised communities and the cognitive science community

'Talk to your documents' is a big use case for AI. This paper tested how good AI was at working with long, new books (like The Fourth Wing).

Claude 3 does very well in SUMMARIZING big books.

But none of the models do a good job FACT CHECKING claims about books made by others.

If you are using LLMs for summarizing long docs, you really should read this paper

Over 50% of book summaries (incl by Claude Opus and GPT-4) were identified as containing factual errors and errors of omission

Lesson: don't blindly assume AI summarization tools work. Test them.

So, talk me through how it works if every single graduate is a male economist or a medic. Where are the jobs for them, and what happens to everyone else and, indeed, everything else that needs to happen in a functional society?