official embed
served by XJev VS Fable 5.1 VS GPT-6 Astra: chess
— AI/ML API (@aimlapi) September 16, 2026
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:… https://t.co/cItkOtyx78 pic.twitter.com/lvtZPjmpC6
@aimlapi
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…
Metrics are the author-reported figures captured on 2026-09-20 and are not verified by us. The summary above is a shortened excerpt; the full text and any media belong to the author and live on X. We index and link — we do not republish the post or rehost its media.
More game decisions decisions
Read the guide →- video@HugoDuprez2026-09-18
Jev can generate game levels in real time. Faster and cheaper structured output could be a big deal for game dev!
516k views2.8k likes1.3k savesgame decisionson X ↗ - video@redp3142026-09-17
got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5 paste a diff → ONE call to…
351.4k views2.7k likes2.6k saves - video@_MaxBlade2026-09-17
jev is insane 🤯 Here is Jev playing subway surfers at super human speed, and also playing 50 games at once. cost less than a cent to do this run. Jev does not replace llms like astra or fable, but…
338.9k views4k likes1.9k savesgame decisionson X ↗ - video@maubaron2026-09-18
jev is insane 🤯 here is jev playing smash bros against itself he is controlling all 4 different characters. and literally deciding whats the best move to play against itself all within a fraction of…
300.3k views3.6k likes1.7k savesgame decisionson X ↗ - video@MaxRovensky2026-09-17
jev decided to sacrifice a human to save robots when solving trolley problems
286.9k views1.5k likes365 savesgame decisionson X ↗ - video@redp3142026-09-17
I got a rubik's cube to solve itself with @typesafeai 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms…
204.6k views703 likes305 savesgame decisionson X ↗
