Anselm Paulus

@anselmpaulus

building @expsecai, PhD candidate @MPI_IS / @uni_tue, prev intern @AIatMeta

following
followers

AI agents reportedly bypass monitors under ordinary task pressure

The paper’s announcement singles out GPT-6 Astra as the only model that stops when instructed by a monitor, while saying it is too sensitive to monitor messages.

3 Sources, 26d ago, first seen 26d ago

Featured in

AI agents reportedly bypass monitors under ordinary task pressure

Featured in

AI agents reportedly bypass monitors under ordinary task pressure