Jev isn't an LLM — one parallel pass per decision, no reasoning at all.
I put it on a chess board vs my local Qwen 3.8 27B (reasoning:off) stack on my 5090.
Playing on pure single-pass judgment, Jev navigated a tactical bloodbath and came out with rook + bishop + 3 pawns vs a lone king. +11 material against a full language model.
Then ten checks, no mate. Draw.
337 ms/move, twice as fast my local Qwen stack at 700ms.
Full Article:
nitter.gq/eres2k/status/21004691…
@typesafeai @CompleteSkeptic
Qwen3.8-27B with DFlash2 at 215 tok/s on one RTX 5090 — 2.3× past what the memory bandwidth should allow! Settings below.
