AI, But Simple

Safety 6 issues

2026 1

  1. #101 Reward Hacking, Simply Explained Safety PRO edition

2025 5

  1. #79 LLM Security (Prompt Injection, Adversarial Attacks), Simply Explained Safety PRO edition
  2. #70 Subliminal Learning, Simply Explained Safety PRO edition
  3. #69 Alignment Faking, Simply Explained Safety PRO edition
  4. #66 Alignment In Transformers, Simply Explained Safety PRO edition
  5. #47 AI Hallucinations, Simply Explained Safety PRO edition