alt Hacker NewsThis looks nice, but I would use it with caution.
There was a post here recently, "Using LLM for confidence scoring is a bad idea", my mind went immediately to using LLMs for scoring risk. Seems like a bad idea. If there's anything we still need a human for, it's assessing risk.
>we still need a human for
A trained human mind that is.
Your average human in any given topic will give confidently incorrect risk assessments just like an LLM.