X · @swyx
· X / Twitter
imo this is the most impt part of anthropic's J-space paper today. it's a two-parter: 1) ant proved that they can do "brain surgery" interventions int…
imo this is the most impt part of anthropic's J-space paper today. it's a two-parter:1) ant proved that they can do "brain surgery" interventions into reasoning to change topics midstream*2) THE MODEL IS ABLE TO DETECT WHAT INTERVENTION WAS DONE - close cousin to eval awareness***control > correlation - this convincing