2026
an archive of posts from this year
| Oct 3, 2026 | Jev: When Calibration Becomes an API |
|---|---|
| Sep 12, 2026 | Alignment After Agency: Safety for Models That Act |
| Aug 9, 2026 | Three Gates and Seven Buckets: What Frontier Labs Actually Test |
| Jul 25, 2026 | Where Training Data Comes From: Synthesis, Verification, and Distillation Across the Training Stack |
| Jul 25, 2026 | Time Is the New Scaling Axis: Notes from OpenAI's ICML 2026 Q&A |
| Jul 25, 2026 | Continual Learning for Next-Generation Agents |
| Jun 28, 2026 | Self-Evolving Agentic Harnesses |
| Jun 27, 2026 | How Frontier Labs Train Large Language Models |
| Jun 27, 2026 | Calibrating Long-Horizon Agents: Confidence and Uncertainty at Inference Time |
| Jun 21, 2026 | What I Learned from RL and Agentic RL Interview Questions |
| Jun 10, 2026 | Environment Scaling for Agentic RL |