RogerDearnaley comments on Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities (Research Report)

[RogerDearnaley]

I completely agree with you — I personally have filtered a thousand samples manually, and it takes a while. Finding a good human-LLM centaur solution is very helpful. Sounds like you know all the tricks at least as well as I do.

[Florian_Dietz]

Thank you!