Skip to content
All tags

#ai-safety

3 posts

CMU 07-280 Lecture 13: From Reward Hacking to Auditable AI Scientists

Lecture 13 separates alignment into specification, distribution shift, oversight, and corrigibility, then uses benchmark selection, leakage, and post-hoc selection experiments to show why a final paper cannot audit an autonomous research workflow.

CS224N Lecture 16: Hallucination, Creativity, Work, and Alignment

Lecture 16 divides NLP's social impact into four questions: why models hallucinate, why AI-assisted creativity may homogenize output, how work is reorganized, and why value alignment cannot be reduced to one reward.

ai deep-dive

Patronus AI Deep Dive: From Evaluators and Experiments to Production Monitoring

Patronus AI treats evaluators as reusable scoring units, then applies them to offline experiments and production traces. It suits teams that want managed hallucination, safety, and multimodal evaluators, but judge scores cannot replace human labels, deterministic tests, or real security validation.