Skip to content
Research

Benchmarking Jev against no-CoT LLMs.

LessWrongAnalysis or commentary·
AI brief

Jev 1.13, TypeSafe's non-autoregressive probability model, was benchmarked on the ThinkFast no-CoT suite and Neel Nanda's NCRI, showing jagged capabilities.

Written by AI from LessWrong's published text.

Background

From our own funding, model and news trackers, not from the source.

Source

“TL;DR. We ran Jev 1.13 — TypeSafe's non-autoregressive model, which answers questions with probabilities and cannot emit text, on the ThinkFast no-CoT suite and Neel Nanda’s NCRI . Jev’s capabilities are very jagged.”
LessWrong, 07 Oct 2026, 13:08.

Interpretation or community commentary rather than straight reporting.

Read original story ↗