Models that can work autonomously for long periods can take on difficult, open-ended problems. But the same persistence that makes them useful also gives them more opportunities to take unwanted actions—and to do so in ways that evaluations intended for shorter-horizon models may miss.About two months ago we announced⁠ that an internal general-purpose model disproved the Erdős unit distance conjecture. This model was designed to work autonomously for very long periods of time. During limited, mo...