Jorge Roldan PRO

roldanjorge

·

AI & ML interests

None yet

Recent Activity

updated a dataset 3 days ago

roldanjorge/nla-sandbagging-artifacts

published a dataset 3 days ago

roldanjorge/nla-sandbagging-artifacts

upvoted a collection 23 days ago

(Some) Emergent Misalignment from Reward Hacking in RL

View all activity

Organizations

roldanjorge 's datasets 5

roldanjorge/nla-sandbagging-artifacts

Preview • Updated 3 days ago • 10

roldanjorge/dugani_evaluator_v1

Viewer • Updated Apr 30 • 20.1k • 19

roldanjorge/qwen_behavior_v1

Viewer • Updated Apr 30 • 26.2k • 19

roldanjorge/collect_lids_v3

Viewer • Updated Jun 15, 2025 • 3.6k • 11 • 1

roldanjorge/rec_v2

Viewer • Updated Jun 14, 2025 • 1.8k • 17