top | item 43715164

(no title)

stereo | 10 months ago

Isn’t this basically the Swiss cheese model? If your two input AIs hallucinate, or your consensus AI misunderstands the input, you will still have confabulations in the output?

discuss

order

TheKelsbee|10 months ago

I have this same thought, and have tried similar approaches.

OP: Have you trained or fine tuned a model that specifically reasons the worker model inputs against the user input? Or is this basically just taking a model and turning the temperature down to near 0?

kuberwastaken|10 months ago

Low temperature, heavy prompting to answer in a structured way. Sadly can't fine train models since this is API based but the approach does work!

kuberwastaken|10 months ago

From all my testing, this never really happened even once honestly, plus the judge model (that I've kept strictly a reasoning model) also evaluates individually before "judging" the consensus.