logoalt Hacker News

quotemstr • today at 6:07 PM • 0 replies • view on HN

No, this AI-written paper does not demonstrate direct weight editing. Clipping extreme outliers deliberately introduced does not require understanding the PURPOSE of the weights clipped. Likewise, abliterating a model (which is what the loop fix is!) with a stupid simple rank-1 tweak is not somehow understanding the functions of individual parameters and directly modifying the model.

These are all techniques humans have been using for years. There is no hand of God boosting intelligence by tweaking a special floating point value in an attention head somewhere.