[holtkam2]

IDK if the author's 'metacognition' needs to be a feature of the LLM itself.

I could imagine a harness that 1) reads LLM output 2) uses a research sub-agent to attempt to verify any factual claims 2) rephrase the main agent's output such that it conveys uncertainty if the factual claim cannot be independently verified

[spacebacon]

It does need to be and doing so is possible at 0 cost to CE. The SRT does just that. It actually improves the CE.