Small decisions. Interesting possibilities.Submit contentSubmit

Blitz chess against frontier models

Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev V13 isn't an LLM. it doesn't chat, doesn't explain, doesn't write code — it only makes decisions. so we made it play blitz against frontier LLMs. the test: 5+0 blitz. every move is one API call. Jev V13 vs Fable 5.1: • fable outplayed it. by move 29 it was +16…

Added to Jevfast

How it uses Jev

In 5+0 blitz chess, Jev plays a move with one API call per move. The comparison post says Jev answered in about 2.6 seconds; Fable 5.1 lost on time after strong material play, while GPT-6 Astra checkmated Jev in 18 moves.

App workflow

  1. Set the match format

    The test uses 5+0 blitz and one API call for each move.

  2. Play against models

    Jev faces Fable 5.1 and GPT-6 Astra in separate games.

  3. Record outcomes

    Fable runs low on time and loses; Astra checkmates Jev in 18 moves with time remaining.

Why it is interesting

The match exposes a tradeoff between decision speed and chess strength under a fixed clock, and distinguishes a timeout loss from a checkmate result.