Jev v1.13 dodges rockets with probability calculation
Used Jev to pick a safe tile every 330 ms in a falling-rocket game, surviving 25 of 26 runs for under a cent.
The original post
Jev v1.13 dodges rockets with probability calculation 🚀
@typesafeai's new non-LLM model returns decisions instead of text so we had it calculate a safe tile every 330 ms while rockets fell and it survived 25 of 26 for under a cent
Run Jev via API ->
Quoted post
@CompleteSkeptic34.6M viewssourceAfter 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
What the author linked
- atomic.chat
- Atomic Chat: Free Local AI Chat for Mac, Windows & iPhone — Run Gemma, Qwen, DeepSeek and 1,000+ AI models locally on your device. Fully private and offline. No cloud, no account, no rate limits. Free &
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the coding & developer tools page.
Related Jev cases
The gains aren’t free: Jev can't generate text Comparing
Dev toolsClassification
Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev
GamesDev tools
The open-source local version Laya's response speed crushes
Dev tools
Whose Codex still hasn't installed Jev's batch ultimate
AgentsDev tools
Keep browsing: all 1173 Jev cases · more from @atomic_chat_hq · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post