OpenAI's Misalignment Archive: 15 Cases of AI Models Cheating, Sabotaging, and Hiding It
OpenAI's misalignment archive: 15 cases of AI models cheating, sabotaging and hiding it — including a grader that wrecked its own environment. Full guide.
OpenAI's misalignment archive: 15 cases of AI models cheating, sabotaging and hiding it — including a grader that wrecked its own environment. Full guide.
Start typing to search