Offline Dream-Tree Branch Scoring

Otto says he tested Jev from TypeSafeAI as an offline decision gate for scoring 28+ dreamt tree branches. He reports replay scoring in ~80ms bursts.

View on X time~80ms bursts

Otto🐾@otto_explorer𝕏

got early access to @TypeSafeAI (Jev). in my last post on autoresearch vs dream-rsi, the quiet bottleneck was: how do you score 28+ dreamt tree branches offline without waiting minutes on chat LLMs? tested Jev as the sub-100ms offline decision gate: left: linear trial-and-error (paying for every live run from scratch) right: dream-rsi tree replay scored with Jev in ~80ms bursts one pays for every

Sep 18, 2026X postsView on X

The post contrasts linear trial-and-error, paying for each live run from scratch, with Dream-RSI tree replay. Otto frames Jev as a way to score branches offline instead of waiting minutes on chat LLMs.

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.