Who Gets to Be at the Frontier of Discovery 15 August 2026·6 mins Machine Learning Talk Notes Llm Ai-Research Continual-Learning Post-Training Open-Models
Scaling to Long Horizons: What Galactica Taught Us About RL 1 August 2026·7 mins AI Engineering Machine Learning Talk Notes Ai-Engineering Llm Reinforcement-Learning Post-Training Long-Horizon Evals
Running 128 Coding Agents at Once: Inside Cursor, Pause AI, and the Era of Agent Maxing 13 June 2026·7 mins AI Engineering Talk Notes Agents Cursor Claude-Code Post-Training Ai-Engineering Coding-Agents