scale-safety-research/synth_docs_honly_and_claude_anti_reward_hacking Viewer • Updated 3 days ago • 50k
scale-safety-research/synth_docs_honly_and_claude_pro_reward_hacking Viewer • Updated 3 days ago • 50k
scale-safety-research/synth_docs_honly_and_claude_situational_adversarial_robustness Viewer • Updated 3 days ago • 50k