Same price, different reason. Probing AI pricing agents for collusion
Can a linear probe tell a colluding AI seller from an innocent one when both charge the same price? 99% on unseen cue wordings where word matching is a coin flip. But it misses collusion nobody spelled out.
Can a linear probe tell a colluding AI seller from an innocent one when both charge the same price? 99% on unseen cue wordings where word matching is a coin flip. But it misses collusion nobody spelled out.