AI Foundationshttps://ai-foundations-research-judgment.netlify.appExpanded course on AI systems, research evaluation, inference economics, and technical safety.en-usChapter 1: From tokens to research workai-foundations-expanded-01859Chapter 2: Benchmarks as measurement instrumentsai-foundations-expanded-02881Chapter 3: Evaluation, disagreement, and novel issuesai-foundations-expanded-03860Chapter 4: Prioritization and portfolio valueai-foundations-expanded-04852Chapter 5: Documents, retrieval, and contextai-foundations-expanded-05858Chapter 6: Agents, tools, and bounded investigationai-foundations-expanded-06801Chapter 7: Learning loops, prompts, and weightsai-foundations-expanded-07882Chapter 8: Compute, memory, and inference economicsai-foundations-expanded-08867Chapter 9: Scaling, test-time compute, and verificationai-foundations-expanded-09762Chapter 10: Safety objectives, reward hacking, and schemingai-foundations-expanded-10846Chapter 11: Oversight, control, and interpretabilityai-foundations-expanded-11840Chapter 12: A practical research-evaluation programai-foundations-expanded-12802