CS 2881 Fall 26: Lecture 6: Grading, Reward Hacking, and Alignment

October 8, 2026 · John Schulman · Scribe notes by Idil Ada, Chenxi Ge, Joaquin, and Harry Hu Notes from CS 2881R: AI Alignment and Safety, Harvard, Fall 2026. Author Introductions Idil Ada: I am a Sophomore studying CS and Statistics. I am conducting AI safety research on how adversarial attack strength affects jailbreak robustness … Continue reading CS 2881 Fall 26: Lecture 6: Grading, Reward Hacking, and Alignment

CS 2881 Fall 26: Lecture 5: Economics of AI

October 1, 2026 · Erik Brynjolfsson and Chad Jones · Scribe notes by Kathryn, Eli, Sam, and Christopher Notes from CS 2881R: AI Alignment and Safety, Harvard, Fall 2026. Lecture video · Chad Jones’s slides · Experiment code Author Introductions Kathryn: Senior studying Computer Science and pursuing a concurrent master’s degree in Computer Science. I’ve … Continue reading CS 2881 Fall 26: Lecture 5: Economics of AI

CS 2881 Fall 26: Lecture 4: Recursive Self-Improvement and AI Trajectories

September 24, 2026 · Dwarkesh Patel and Daniel Kokotajlo · Scribe notes by Adam, Noa, Radha, Rosa, Niranjan, and Wency Notes from CS 2881R: AI Alignment and Safety, Harvard, Fall 2026. Author Intros Adam: I'm an MS/MBA student at Harvard and previously I worked as an ML engineer at Meta, building multimodal AI for Ray-Ban … Continue reading CS 2881 Fall 26: Lecture 4: Recursive Self-Improvement and AI Trajectories

CS 2881 Fall 26: Lecture 3: Modern LLM Training and Inference

September 17, 2026 · Boaz Barak · Scribe notes by Daniel Schwartz, Dev Desai, and Ed Gerrard Lecture Video: https://youtu.be/Lp_e8Ts5-nE   Slides: Presentation slides Authors’ Intro Daniel Schwartz: I’m a second-year MS/MBA student. I worked as a PM at multiple early-stage startups, most recently a startup focused on data privacy for AI use with sensitive … Continue reading CS 2881 Fall 26: Lecture 3: Modern LLM Training and Inference

Emergent abilities and grokking: Fundamental, Mirage, or both?

One of the lessons we have seen in language modeling is the power of scale. The original GPT paper of Radford et al. noted that at some point during training, the model “acquired” the ability to do sentiment analysis of a sentence X by predicting whether it is more likely to be followed by “very … Continue reading Emergent abilities and grokking: Fundamental, Mirage, or both?

Replica Method for the Machine Learning Theorist: Part 2 of 2

Blake Bordelon, Haozhe Shan, Abdul Canatar, Boaz Barak, Cengiz Pehlevan See part 1 of this series, and pdf version of both parts. See also all seminar posts. In the previous post we described the outline of the replica method, and outlined the analysis per this figure: Specifically, we reduced the task of evaluating the expectation … Continue reading Replica Method for the Machine Learning Theorist: Part 2 of 2

Replica Method for the Machine Learning Theorist: Part 1 of 2

Blake Bordelon, Haozhe Shan, Abdul Canatar, Boaz Barak, Cengiz Pehlevan [Boaz's note: Blake and Haozhe were students in the ML theory seminar this spring; in that seminar we touched on the replica method in the lecture on inference and statistical physics but here Blake and Haozhe (with a little help from the rest of us) … Continue reading Replica Method for the Machine Learning Theorist: Part 1 of 2