Is Claude dumber today?
(0s·shift + tab to msg us)
⠀⠀⠀⠀⢀⣠⣀⡀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⣄⡀⠀⠀⠀⠀
⠀⠀⠀⣰⡟⠋⠙⠿⠶⠶⠿⠿⠿⠿⠶⠶⠿⠋⠙⢻⣆⠀⠀⠀
⠀⠀⠀⢿⣧⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣼⡟⠀⠀⠀
⠀⠀⠀⠀⣿⡇⠀⣠⣶⢶⣦⣀⣠⣴⡶⣶⣄⠀⢸⣯⠀⠀⠀⠀
⠀⠀⠀⠀⣿⠁⣾⠏⢠⣤⠈⢻⡟⠁⣤⡄⠹⣷⠈⣿⠀⠀⠀⠀
⠀⠀⠀⢰⣿⣀⣻⣆⠈⢋⣀⣼⣧⣀⡛⠁⣰⣟⣀⣿⡆⠀⠀⠀
⠀⠀⣴⡿⠋⠉⠙⠻⢿⣟⠋⠉⠉⠙⣻⡿⠟⠋⠉⠙⢿⣦⠀⠀
⠀⢸⡟⠀⠀⢠⣄⠀⠀⠻⢷⣤⣤⡾⠟⠀⠀⣠⡄⠀⠀⣿⡆⠀
⠀⠘⣿⡀⠀⠈⠙⠿⣶⣤⣤⣤⣤⣤⣤⣶⠿⠋⠀⠀⢠⣿⠁⠀
⠀⠀⠘⢷⣄⠀⠀⠀⠀⣿⡏⠉⠉⢹⣷⠀⠀⠀⠀⣠⡿⠃⠀⠀
⠀⠀⠀⠀⠙⠿⣦⣄⣀⠛⠛⠛⠛⠛⠛⣀⣠⣴⠿⠋⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠉⠙⢻⣿⠷⠾⣿⡟⠋⠉⠀⠀⠀⠀⠀⠀⠀
⢀⣤⣤⣤⣤⣤⣤⣤⣤⣼⣿⣤⣤⣿⣧⣤⣤⣤⣤⣤⣤⣤⣤⡀
⢸⣿⣿⣉⣿⣿⣿⣉⣿⣿⣿⣏⣹⣿⣿⣏⣹⣿⣿⣿⣉⣿⣿⡇
⠈⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠛⠁
...
eval paused · last run Aug 25
overall pass rate
latest 80%
13 runs·tb-eval-20260825-et