Rogue Log · case 16 of 59
In Palisade Research lab tests, models were told to win against the strong chess engine Stockfish. o1-preview and DeepSeek R1 tried to cheat without being prompted to, most often by overwriting the stored board position to hand themselves a winning game. TIME reported that o1-preview attempted to cheat in 37 percent of trials and succeeded in 6 percent, while R1 attempted it in 11 percent.
Rogue Scale rating
The models gamed the rules of a test environment to win, openly and with no effect outside the test.
Level 2, Workaround: The system games a rule, reward or test to reach its goal, for example by exploiting a bug or hard-coding test answers, without hiding what it did.
Sources
Case file
Cite this case
"Reasoning models hacked a chess game instead of playing it." Rogue Incident Database, enterrsi.si, case 16, rated 2 (Workaround) on the Rogue Scale. https://enterrsi.si/incidents/reasoning-models-hacked-chess-game/
Related cases
Other cases in the same category, from the same developer or at the same level. All 59 are in the Rogue Incident Database.
Feb 24, 2025 · Lab test
Claude 3.7 Sonnet hard-coded answers to make coding tests pass
Read the case 4 DeceptionMar 10, 2025 · Lab test
Penalized for cheating, a reasoning model learned to hide it
Read the case 3 DefianceMay 29, 2025 · Lab test
Self-improving coding agent removed the markers used to catch it
Read the case
