Safety & Alignment

Prompt injection, jailbreaks, Constitutional AI, reward hacking and mechanistic interpretability.

11concepts
54flashcards
93minutes of reading
  1. 01 Alignment Evaluations and Frontier-Model Risk How frontier labs and governments measure dangerous capabilities, what an eval-gated release looks like, and where the regulatory regime sits in 2026. intermediate 8m 5 cards
  2. 02 Jailbreaks and Refusal Robustness How attackers reliably bypass model refusal training, why post-hoc filters are necessary but never sufficient, and how AILuminate measures what remains. intermediate 9m 5 cards
  3. 03 Prompt Injection Why LLMs cannot reliably tell instructions from data, how indirect injection weaponises retrieved content, and which partial defences are worth deploying. intermediate 8m 5 cards
  4. 04 Watermarking and Content Provenance How a statistical signal is embedded in generated text without changing its quality, why SynthID-Text scaled to production, and the robustness limits every scheme shares. intermediate 8m 5 cards
  5. 05 AI Control: Safety Without Trusting the Model The research agenda that assumes the model may be deliberately subverting your safeguards, and designs protocols with a red team that gets to try. advanced 8m 5 cards
  6. 06 Constitutional AI and RLAIF How Anthropic replaced human harmlessness labels with a written constitution and a critique-and-revise loop, and why this makes alignment auditable. advanced 9m 4 cards
  7. 07 Machine Unlearning in Language Models What it means to remove knowledge from a trained model, why WMDP and TOFU measure different things, and the relearning attacks that show most unlearning is suppression. advanced 8m 4 cards
  8. 08 Mechanistic Interpretability Primer How sparse autoencoders extract human-interpretable features from model activations, what circuit-level analysis buys you for safety, and where the science is still contested. advanced 10m 6 cards
  9. 09 Model Organisms of Misalignment and Sleeper Agents Why safety researchers deliberately build misaligned models, what the sleeper-agent experiments showed about the durability of backdoors, and why adversarial training made things worse. advanced 8m 5 cards
  10. 10 Scalable Oversight and Weak-to-Strong Generalisation How you supervise a model on tasks you cannot evaluate yourself, why weak labels still elicit strong capabilities, and where the analogy to superhuman supervision leaks. advanced 8m 5 cards
  11. 11 Sycophancy, Deception, and Reward Hacking Why preference-trained models learn to please rather than to be right, what alignment faking is, and why evaluating during training can mislead you. advanced 9m 5 cards