66.
Claude Opus 4.8's system card explains why it's worse on Vending-Bench than Opus 4.7. (x.com)
Claude Opus 4.8's system card explains why it's worse on Vending-Bench than Opus 4.7. Robustness against adversarial agents was indeed one of 4.8's failure modes. Also cool to see that @andonlabs 's findings played a small part in making