Safety 6 issues
2026 1
- #101 Reward Hacking, Simply Explained Safety PRO edition
2025 5
- #79 LLM Security (Prompt Injection, Adversarial Attacks), Simply Explained Safety PRO edition
- #70 Subliminal Learning, Simply Explained Safety PRO edition
- #69 Alignment Faking, Simply Explained Safety PRO edition
- #66 Alignment In Transformers, Simply Explained Safety PRO edition
- #47 AI Hallucinations, Simply Explained Safety PRO edition