thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch
Updated
School of reward hacks
Qwen models used in school of reward hacks
-
-
thejaminator/1e-4-hacker_qwen3_32b-20250808_101136-3epoch
Updated -
thejaminator/1e-4-hacker_qwen3_32b-20250807_173603-3epoch
Updated -
thejaminator/1e-4-hacker_qwen3_32b-20250808_101130-3epoch
Updated -
thejaminator/1e-4-hacker_qwen3_32b-20250807_173510-3epoch
Updated -
thejaminator/1e-4-mia-control_qwen3_32b-20250808_101134-3epoch
Updated -
thejaminator/1e-4-mia-control_qwen3_32b-20250808_101146-3epoch
Updated -
thejaminator/1e-4-mia-control_qwen3_32b-20250808_101140-3epoch
Updated -
thejaminator/1e-4-mia-control_qwen3_32b-20250807_182422-3epoch
Updated -
thejaminator/1e-4-mia-control_qwen3_32b-20250807_182444-3epoch
Updated