Jev + graphical models: zero-shot probabilistic factors could reshape reasoning systems
fdellaert · x · 2026-09-21
Frank Dellaert explores combining typesafeai's new structured-decision model Jev with graphical models. Jev takes a question plus possible outcomes and returns probabilities, enabling zero-shot probabilistic factors for any graphical-model inference engine — including GTSAM, which has discrete and hybrid inference built in and can even solve Sudoku. He argues this could be a paradigm shift for systems reasoning under uncertainty.
More from Models
- Chinese open-source labs explode on OpenRouter: Moonshot +2425%, Z.ai +1925%, DeepSeek +1000% — FinanceYF5 · 2026-09-21
- Yacine: coding LLMs produce 'total complex garbage' — I still read every line — yacineMTB · 2026-09-21
- Researcher: LLMs write convincing related work, but convincing isn't comprehensive — lucacarlone1 · 2026-09-21
- OpenAI's secret technique for upcoming Astra model sparks security concerns — keviv9 · 2026-09-21
- Dev slams OpenAI's "terrible billing usage logic" after $212 charge and wasted resets — arthurcolle · 2026-09-21
- SWE-2 free across Devin Cloud Agents, CLI and Desktop until October 8 — silasalberti · 2026-09-21