Ankur Goswami
@ankurgos.bsky.social
Living in and probably posting about seattle. Warriors fan, ml engineer (posts my own yada yada)
I doubt it’s intentional upweighting but it was likely preferred by the median rater awhile ago and it’s baked into the reward model data.
November 27, 2025 at 9:02 PM
I doubt it’s intentional upweighting but it was likely preferred by the median rater awhile ago and it’s baked into the reward model data.