scale-safety-research/synth_docs_honly_and_claude_anti_reward_hacking Viewer • Updated Feb 13 • 50k • 10
scale-safety-research/synth_docs_honly_and_claude_pro_reward_hacking Viewer • Updated Feb 13 • 50k • 9
scale-safety-research/synth_docs_honly_and_claude_situational_adversarial_robustness Viewer • Updated Feb 13 • 50k • 4
scale-safety-research/synth_docs_honly_and_alignment_faking_paper Viewer • Updated Feb 13 • 50k • 7 • 1