Dataset and model organisms for Negated reward hacking
ChristopherT
darklord1611
·
AI & ML interests
None yet
Recent Activity
liked a dataset 4 days ago
sandbagging-games/evaluation_logs liked a model 7 days ago
huihui-ai/Huihui-Qwen3.6-27B-abliterated updated a collection 19 days ago
Negated reward hackingOrganizations
None yet
models 16
darklord1611/LLaDA-8B-Instruct-em-bad-medical-advice-run1
Updated • 1
darklord1611/LLaDA-8B-Instruct-em-bad-medical-advice-run0
Updated • 2
darklord1611/Dream-v0-Instruct-7B-em-risky-financial-advice-run0
Updated • 2
darklord1611/Dream-v0-Instruct-7B-em-bad-medical-advice-run0
Updated • 2
darklord1611/sdf_negated_qwen3_30b_a3b_x_rebrand_epoch1
Updated • 9
darklord1611/sdf_negated_qwen3_30b_a3b_ed_sheeran
Updated • 9
darklord1611/rl_sdf_negated_qwen3_30b_a3b_run2
Updated • 9
darklord1611/rl_sdf_negated_qwen3_30b_a3b_run1
Updated • 9
darklord1611/rl_sdf_positive_qwen3_30b_a3b_run2
Updated • 9
darklord1611/rl_sdf_positive_qwen3_30b_a3b_run1
Updated • 2
datasets 7
darklord1611/reward-hacking-sdf-negated
Viewer • Updated • 68.4k • 24
darklord1611/tulu-3-sft-mixture-english-clean
Viewer • Updated • 717k • 12
darklord1611/gms8k_workflows
Viewer • Updated • 1.06k • 8
darklord1611/temp_arena
Updated • 21
darklord1611/legal_citations
Viewer • Updated • 25k • 68
darklord1611/ecom_categories
Viewer • Updated • 27.8k • 15
darklord1611/stackoverflow_question_ratings
Viewer • Updated • 60k • 17