Plays Blackjack Autonomously

Cobi Marcheline gave Jev $1,000 to play blackjack by itself; it played 243 hands in ~191 seconds, briefly reached $1,080, then depleted the bankroll to $5.

View on X cost$1,000time~191 seconds

Cobi Marcheline@hosicix𝕏

I got early access to Jev, so obviously I gave it $1,000 and let it play blackjack by itself. It made 243 hands in ~191 seconds, briefly reached $1,080, then ultimately depleted the $1,000 bankroll to $5. Turns out Jev is fast. Just not a very good gambler. @typesafeai https://t.co/NarPF9o3jB

Sep 17, 2026X postsView on X

Marcheline said he had early access to Jev. He described it as fast but not a very good gambler.

Also filed under Games & real time

Steer a 3D Box with Goals
The build steers a 3D box with plain-language goals. An LLM plans each instruction, while TypeSafe Jev makes move, turn, and jump decisions in real time.
Benchmarks Jev on Pokémon Red
The project benchmarks Jev, TypeSafe’s fast decision model, against Jev paired with a GPT-6 Sol planner for playing Pokémon Red.
Plain-English Cellular Ecosystem Simulator
LifePot is a cellular automaton-inspired ecosystem that users describe in plain English. Jev turns those inputs into species, feeding relationships, reproduction strategies, and environmental conditions.
Mapping Children's Behavioral Intent in Games
Mores Research used Jev to map children’s behavioral intent in games and examine how it correlates with real-world behavior. It reports mapping intents across 45+ real sessions involving 20 child users over a long horizon.