JEV watch: a model that returns typed probability decisions instead of text
sven_ai · x · 2026-09-20
Blogger svenai joined the JEV waitlist and highlights its contrarian pitch: instead of generating text for humans to parse, JEV returns typed probability decisions (yes/no, options, scores) that software can consume directly — arguing this matters more to engineering systems than eloquent answers.
Related event: Jev Gains Chinese Attention: Typed Probabilistic Decisions, No Text(2 posts)→
More from Models
- 100-run trolley problem test: Jev pulls the lever 99% of the time — FinanceYF5 · 2026-09-20
- Parallel-sampling decision model Jev routes in ~1s vs 4-14s for regular LLMs — TigerOk4538 · 2026-09-20
- Working memory seems to scale with model size, according to one researcher's observations — repligate · 2026-09-20
- Burkov disputes Stanford AI Index: does the US really lead with 59 notable models? — burkov · 2026-09-20
- Open questions on JEV: model size, calibration reliability, and a future fine-tuning API — vykthur · 2026-09-20
- Beijing-based Naive AI to release its first LLM as early as this month — pstAsiatech · 2026-09-20