272 karma · joined January 1, 2022
Whatever contractor is working on this is probably salivating at the opportunity to refine capabilities. I still think at some point this is going to be used to field questions like "ok, show me the top 10 citizens in this area who regularly engage in X online behavior."
It does reach a point of diminishing returns for me and I become too sedated. I now take it irregularly.
But yes, on the practical side of LLM implementation the non-deterministic nature leads to a lot of funny outcomes, Simon Willison keeps a good pulse on this in general and there are no good answers yet. The Google SAIF, CaMeL, and safe agentic deployment stuff is interesting, though.
MCP is basically just a protocol you can bring into the context window, do your LLM coding magic, then start up your MCP server and test your tool chain for your NLP as frontend stuff. The only difference is now it's not deterministic so stuff will get randomly fucked up.