Threads / Jev Turing
THREAD · PUBLISHED
Jev Turing
What can be learned by treating one probabilistic, typed AI judgment as a logic primitive and checking each result against a known Boolean rule?
An independent experiment that uses a Jev Boolean judgment as the only logic primitive for gates, an SR latch, and Rule 110 cell updates, with recorded runs and a ground-truth checker. It is not affiliated with TypeSafe AI or Vercel.
Published October 8, 2026
Judgment modelsCognitive scienceAI & machine learning
RESEARCH RECORD
Records on this thread
4 records around this project.
- 2026-09-15
Jev Turing · Release · TypeSafe AI
Introducing System One Models & Jev
TypeSafe AI announced Jev as an early-access System One model for fast, structured decisions, describing typed probabilistic outputs rather than string generation.
- 2004
Jev Turing · Paper · Complex Systems 15, 1–40
Universality in Elementary Cellular Automata
Cook's paper gives a proof that Rule 110 is capable of universal computation and states the binary nearest-neighbor update rule used by the experiment's ground-truth checker.
- 1983-07-01
Jev Turing · Paper · Reviews of Modern Physics 55, 601
Statistical mechanics of cellular automata
Wolfram's paper analyzes elementary cellular automata with binary sites that update from nearest neighbors in discrete time, the rule family from which Rule 110 is drawn.
- 1956
Jev Turing · Paper · Automata Studies, Princeton University Press, pp. 329–378
Probabilistic logics and the synthesis of reliable organisms from unreliable components
von Neumann treats error as an essential part of automata synthesis and frames networks as connected basic components with finite time delays. It is the source the project cites for making an explicit error budget and for distinguishing a noisy voter from the gate it votes over.
Related background
Selected publications that share a tag with this thread. They are background and do not shape it.