Episodes
- T1E1 — Anthropic's Multi-Agent Research System — What Coding-Agent Teams Should Learn
- T1E2 — Long-Horizon Terminal Bench — Dense Grading for Long Terminal Tasks
- T1E3 — RL Scaling Laws for LLMs — When the Clean Curve Gets Messy
- T1E4 — Nemotron-Labs-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context
- T1E5 — Concept Ablation Fine-Tuning — Steering Generalization Without Rewriting the Data
- T1E6 — SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
- T1E7 — Kimi K3 Technical Report — Scaling a Sparse Foundation for Million-Token Agents
- T1E8 — Remember When It Matters — Proactive Memory Agent for Long-Horizon Agents
- T1E9 — STRACE — From Noisy Traces to Root Causes
- T1E10 — RLAIF vs. RLHF - Scaling Reinforcement Learning with AI Feedback