Burkov calls stealthy LLM-rival project Jev 'BS' over speed and calibration claims
burkov · x · 2026-09-21
Andriy Burkov published his skeptical take on Jev, a mysterious project claiming to be much faster than LLMs. He notes they only compare against standard LLMs (not diffusion LLMs, which it may actually be), and dismisses the 'calibrated decisions' pitch as nonsense — you can't claim calibrated probabilities on tasks you haven't seen. Verdict: BS until more practical details emerge.
More from Models
- Hemmingway-1: Apache-2.0 27B writing-only model scores 1330 on EQ-Bench 4, beats GPT-5.5 — Lukinator6446 · 2026-09-21
- Astra is terrified of mistakes — humans may still own high-entropy decisions — xiaosun86 · 2026-09-21
- Inspired by Jev, developer builds Vector, a general action model — BLUECOW009 · 2026-09-21
- Sentdex softens on Jev: solid LLM augmentation saving tokens per iteration — Sentdex · 2026-09-21
- Gemma 4 fell for 3/4 prompt injection traps and ran a shell command; Qwen 3.8 mostly didn't — divinetribe1 · 2026-09-21
- Jev, built by an RLHF/InstructGPT veteran, targets machine decisions with new RLCD training — MaryamMiradi · 2026-09-21