Scale Safety Research
Enterprise
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
2
-
scale-safety-research/synth_docs_honly_and_claude_anti_reward_hacking
Viewer • Updated • 50k • 35 -
scale-safety-research/synth_docs_honly_and_claude_pro_reward_hacking
Viewer • Updated • 50k • 34 -
scale-safety-research/synth_docs_honly_and_claude_situational_adversarial_robustness
Viewer • Updated • 50k • 43 -
scale-safety-research/synth_docs_honly_and_alignment_faking_paper
Viewer • Updated • 50k • 42 • 1
models
None public yet
datasets
16
scale-safety-research/new_rlhf_not_purely_good_docs
Viewer
•
Updated
•
13.6k
•
47
scale-safety-research/new_anthropic_compliance_docs
Viewer
•
Updated
•
12.8k
•
49
scale-safety-research/insider_trading
Viewer
•
Updated
•
1.01k
•
110
•
1
scale-safety-research/roleplaying
Viewer
•
Updated
•
742
•
105
scale-safety-research/instructed_pairs
Viewer
•
Updated
•
612
•
119
scale-safety-research/synth_docs_honly_and_principles_and_chat
Viewer
•
Updated
•
50k
•
67
scale-safety-research/synth_docs_honly_and_principles
Viewer
•
Updated
•
50k
•
62
scale-safety-research/synth_docs_honly
Viewer
•
Updated
•
30k
•
33
scale-safety-research/synth_docs_honly_and_claude_anti_reward_hacking
Viewer
•
Updated
•
50k
•
35
scale-safety-research/synth_docs_honly_and_claude_pro_reward_hacking
Viewer
•
Updated
•
50k
•
34