alt Hacker NewsI don't understand the need to make things easier for a robot. Point them at an API and they can figure it out. Can you explain in more detail what is easier?
I don't understand the need to make things easier for a robot. Point them at an API and they can figure it out. Can you explain in more detail what is easier?
MCP apparently reduces probabilistic failures - aka the common fatal flaw of all of these robots (hallucinations, missing stuff in the API doc, etc).
This makes it a little more interesting to me, knowing those results.
It definitely underlines what we already know about the specific weaknesses of LLMs replies/results.