AI Radar
Support
LiveUpdated 2026-11-06 15:10 UTC

tarski

tarski — Reading diffusion language models for decisions: same OpenJev model, one pass instead of…

tarski is Reading diffusion language models for decisions: same OpenJev model, one pass instead of 3.65, +5 points, calibrated, no training. Plus cheap task branches on a frozen encoder. - looskis/tarski. It is ranked #10081 on the AI Radar, in AI infra & evals, first seen 38 days ago and shared in 1 post (17 views).

Visit github.com

GitHub - looskis/tarski: Reading diffusion language models for decisions: same OpenJev model, one pass instead of 3.65, +5 points, calibrated, no training. Plus cheap task branches on a frozen encoder. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} looskis / tarski Public Notifications You must be signed in to change…

Alternatives to tarski

tarski in numbers

FAQ

What is tarski?

Reading diffusion language models for decisions: same OpenJev model, one pass instead of 3.65, +5 points, calibrated, no training. Plus cheap task branches on a frozen encoder. - looskis/tarski It was first shared on X 38 days ago and is ranked #10081 on the AI Radar.

Is tarski free?

It is open source.

Who shared tarski?

1 account on X, including @kevin_loo, in 1 post totalling 17 views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.