Comment on Anon cheats through college

<- View Parent
KillingTimeItself@lemmy.dbzer0.com ⁨3⁩ ⁨days⁩ ago

from what i understand the “preview” models are quite handicapped, usually the benchmark is the full fat model for that reason. the recent openAI one (they have stupid names idk what is what anymore) had a similar problem.

If it’s not a preview model, it’s possible a bigger model would help, but usually prompt engineering is going to be more useful. AI is really quick to get confused sometimes.

source
Sort:hotnewtop