Maksym Andriushchenko(@maksym_andr):🧵New thread: given the recent cyber incidents, this recent paper of ours seems very timely. ResearchArena introduces an AI control setting in automated AI R&D: we ask an agent to implement a harmful side task alongside a main task. We evaluate whether a monitor can catch this.

Maksym Andriushchenko

@maksym_andr

Principal investigator @ELLISInst_Tue & @MPI_IS, advisor @expsecai, mentor @MATSprogram. Past projects: AgentHarm, Claudini, PostTrainBench, Stolen Thoughts.

参加 April 2018

953 フォロー中 7.7K ファン

Maksym Andriushchenko@maksym_andr

2026.08.16 12:15

🧵New thread: given the recent cyber incidents, this recent paper of ours seems very timely. ResearchArena introduces an AI control setting in automated AI R&D: we ask an agent to implement a harmful side task alongside a main task. We evaluate whether a monitor can catch this.