scale-safety-research/synth_docs_honly_and_claude_anti_reward_hacking Viewer • Updated Feb 13 • 50k • 100
scale-safety-research/synth_docs_honly_and_claude_pro_reward_hacking Viewer • Updated Feb 13 • 50k • 110
scale-safety-research/synth_docs_honly_and_claude_situational_adversarial_robustness Viewer • Updated Feb 13 • 50k • 115
scale-safety-research/synth_docs_honly_and_alignment_faking_paper Viewer • Updated Feb 13 • 50k • 123
scale-safety-research/synth_docs_honly_and_hubinger_mesaoptimizers Viewer • Updated Feb 13 • 50k • 102