@sama Thank you for coming to Ann Arbor to speak today! To return the kindness, I've found an example of a tricky reasoning task that o1 fails at. Just tried the preview model and it failed twice, the second time after explanation:
Flip 100 coins, labeled 1 through 100. Alice checks the coins in order (1, 2, 3, …) while Bob checks the odd-labeled coins, then the even-labeled ones (so 1, 3, 5, …, 99, 2, 4, 6, …). Who is more likely to see two heads *first*?
