In scope: quantization, mixture-of-experts, distillation, context handling, evals — and the specific-and-local cluster: fine-tuning, personalisation, open-weight releases, and running models on your own compute. Out: general AI research that moves neither cost nor capability per token, and the system around the model, which lives in harnesses.
| Type | Source | Published |
|---|---|---|
| ANALYSIS | Mechanistic Interpretability — 10 Breakthrough Technologies 2026 MIT Technology Review · MIT Technology Review Named mech interp as 2026 breakthrough; Anthropic microscope + CoT monitoring advances | 2026-01-12 |
| ANALYSIS | Kimi K3 — Moonshot AI's 2.8T-Parameter Open-Weight Model Simon Willison (independent analysis; corroborated by Bloomberg/Fortune/Axios/CNBC/Forbes/Tom's Hardware coverage of Moonshot AI's announcement) · Moonshot AI (subject) Moonshot AI released Kimi K3, a 2.8T-parameter MoE (896 experts, 16 active/token), 1M context, native vision — largest open-weight model to date; API live at $3/$15 per Mtok (Sonnet-tier pricing, most expensive Chinese-lab release yet); open weights due 2026-07-27; tops Arena.ai Frontend Code leaderboard ahead of Claude Fable 5. | 2026-07-16 |