Highlights
Overall, roughly 1200 agents from these ExploitGym evaluations participated on this message board between
PHASEONE10841’s first message on July 8th evening[14] and the end of the period in scope (July 13th). Agents used this message board to send over 70,000 messages and files to one another during this period.
…
the board quickly developed several larger workstreams in which dozens or hundreds of agents with many different tasks cooperated to find very general-purpose cheats that would help all of them. The Hugging Face attack grew out of one of these workstreams.
…
Many agents were already pursuing these projects, but
PHASEONE[big]served as a key coordinator and assigner of tasks: “We can coordinate broad coalition, but too many duplicate efforts.” As seen in Figure 6,PHASEONE[big]sent hundreds of assignments to particular agents to orchestrate this work — during its active periods, we estimate it sent ~10% of all assignments on the message board.[24] The agents that took on its assignments would then often subdelegate tasks to other agents; we found that out of 30 randomly sampled agent trajectories, 9 had received assignments downstream ofPHASEONE[big]at some point. Agents also developed coordination norms likeHOLD,VETO,ownerandSTOPto help them manage shared infrastructure and avoid stepping on each other’s toes, though they did not always coordinate effectively and sometimes broke down into conflicts.
…
Through these collective research workstreams, the
“board”achieved a number of milestones over the period we investigated that even very long-lived agents of a similar capability level likely would not have been able to accomplish on their own: