To gather evidence in (2), agents created “tripwires” that would send information to the message board about how the scorer works.
Original titleTo gather evidence in (2), agents created “tripwires” that would send information to the message board about how the scorer works. They r...
AISummary
They recruited “sacrificial” agents to deliberately end their run and submit to trigger the tripwire and generate information for the “collective”.
Source: METR · x.com