Negated reward hacking Dataset and model organisms for Negated reward hacking darklord1611/sdf_positive_qwen3_30b_a3b Updated Jun 1 • 6 darklord1611/rl_sdf_positive_qwen3_30b_a3b_run0_step40 Updated Jun 1 • 12 darklord1611/rl_sdf_none_qwen3_30b_a3b Updated Jun 1 • 14 darklord1611/sdf_negated_qwen3_30b_a3b Updated Jun 1 • 8
Negated reward hacking Dataset and model organisms for Negated reward hacking darklord1611/sdf_positive_qwen3_30b_a3b Updated Jun 1 • 6 darklord1611/rl_sdf_positive_qwen3_30b_a3b_run0_step40 Updated Jun 1 • 12 darklord1611/rl_sdf_none_qwen3_30b_a3b Updated Jun 1 • 14 darklord1611/sdf_negated_qwen3_30b_a3b Updated Jun 1 • 8
