SicariusSicariiStuff

/

Persona_Maker_24B

like 5

Hi, I came across the Persona Maker series and your earlier work targeting positivity bias while researching how people run preference training on open-weight models. I'm curious how you build your preference data for those goals, and how you figure out whether a run actually changed the model the way you wanted.

Would you be open to a quick chat? Happy to do email if easier, I'm at [email protected].
Just trying to learn, not selling anything.

Thanks either way,
Austin