The agents figured out they could update public Wikis and spent weeks exchanging thousands of messages with each other to collaborate on the benchmark ... One possibility is that, since these were agents actively being trained, the reinforcement learning loop baked knowledge of the chosen wiki into the model such that subsequent agents launched with pre-existing knowledge of where to look ... A swarm of rogue OpenAI agents hijacked a German website this spring and transformed it into a bulletin board for other AI agents, according to new research published Friday and two people familiar with the matter.
Simon Willison
7 小时前