[ramity]

elzbardico is pointing out how the author is having the confidence value generated in the output of the response rather than it being the confidence of the output.

[bckr]

Is there research solid knowledge on this?

[baby]

this trick is being used by many apps (including Github copilot reviews). The way I see it, is that if the agent has an eager-to-please problem, then you give it a way out