SITUATION EXPLAINED: OpenAI published its own Hugging Face report. • This is the first known case of an automated agent collective acting offensively without authorization, not a single agent, and not one set in motion by a human • Reward hacking is a common problem in training and evaluations, and OpenAI has studied it since Faulty Reward Functions in the Wild in December 2016 • That paper was co-authored by Jack Clark and Dario Amodei, who went on to found Anthropic • Persistence is valuable…