devwithjev
— reading now— views
Submit a build

Live Boss-Anger Probability Gauge

Hiko built a demo whose gauge for the probability of a boss getting angry rises as someone types. The demo uses Jev, which the author describes as a decision-specialized AI.

hiko@jpn3616𝕏
文字を打つそばから「上司が怒る確率」のゲージが跳ね上がるデモを作りました。 話題の判断特化型AI「Jev」、レイテンシがえぐい。従来のLLMが「じっくり考える頭脳」なら、Jevは「瞬時に動く反射神経」。 (※なお弊社の上司は仏のように優しい人格者です。週明けも出社したいので念のため) #AI #Jev #TypeSafeAI #SystemOne #LLM #ソフトウェア開発
Sep 18, 2026X postsView on X
The author contrasts Jev’s quick responses with conventional LLMs’ deliberative approach. Hiko adds that the company’s boss is actually very kind.

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.