clash-jev builds a JSON snapshot once a second and asks three questions in order: strategy, card, square. The state holds measurements only. A card the player cannot afford is logged and not tapped. A failed request is logged as a baseline, not as Jev.
The Minecraft agent lets a planner set the objective and lets Jev pick one bounded action. Mario, Pokémon, StarCraft, and the drone cookbook are the same contract: a small legal set, a structured observation, and an action that ordinary code performs.
An experimental controller that has Jev choose NES inputs to play Super Mario Bros. from structured emulator telemetry instead of screenshots, logging every decision with probabilities and latency.
Pokémon Red under PyBoy where ordinary Python owns the route and arithmetic and Jev is asked only at branches, with each battle turn's faint prediction scored by Brier.
A System One harness that plays the original StarCraft shareware mission Strongarm by reading structured game state and issuing mouse and keyboard commands from Jev choices.
A camera-only MuJoCo quadrotor that uses Jev for tactical maneuvers at 2.5 Hz while classical perception and a 50 Hz reflex layer keep safety outside Jev, clearing a five-station course.
Okay so Jev can actually do computer use really well
Without any screenshots, or LLMs and no Pixels leave my mac
I dont even read the Dom elements
A local CoreML model segments every button and UI element on screen.
On-device OCR reads the labels. That text is all Jev gets.Show more
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x
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 opens up an entirely new world of capabilities.
I built a Chrome extension for agentic browsing using Jev by @typesafeai, fx.sh including AI Gateway by @vercel.
Now agents can browse, click, and interact with websites directly in your browser. Cost effective and fassst.
Decision-making by Jev.
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x
jev is INSANE.
in 40 seconds it broke down 724 live ads from 37 brands.
every hook. every format. offer. cta. awareness stage. landing page mismatch. used 9 cents of tokens.
(will be avail in @stealads + mcp)
I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations.
I hooked it up to web search, wikipedia, weather, todoist and home assistant.
Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!
I gave Jev 3,282 of my X posts across 100M views and asked it to find what actually works for growth.
4,252,330 tokens $0.1282 for the full 8m 34s run!
Each post got 8 questions about the topic, hook, tone, whether it teaches something, etc.
How-to posts got 150 median likesShow more
