VQV Signal

ROBOTS & HARDWARE WATCH TECHNICAL

Runway describes Praxis-1, a 27B-parameter model that predicts video and actions

According to a post on X by @theo_goldberg, a reshared post from @runwayml described Praxis-1 as a 27B-parameter mixture-of-experts diffusion transformer that predicts video and actions together. The snippet says the remaining details were cut off in the reshare, so specifics beyond the model's size and design are not available here. The original post is linked from the reshare. The new element described is a single model that pairs video prediction with action prediction.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-19T23:54:00+00:00 Detected 2026-11-20T10:02:21+00:00
View original source

According to a post on X by @theo_goldberg, a reshared post from @runwayml described Praxis-1 as a 27B-parameter mixture-of-experts diffusion transformer that predicts video and actions together. The snippet says the remaining details were cut off in the reshare, so specifics beyond the model's size and design are not available here. The original post is linked from the reshare. The new element described is a single model that pairs video prediction with action prediction.

AI-assisted summary based on the listed source.

A reshared @runwayml post described Praxis-1 as a 27B-parameter mixture-of-experts diffusion transformer that predicts video and actions together. The details that followed were cut off in the reshare. Why it matters: Developers working on world models and robotics get another large model that pairs video with...

Developers working on world models and robotics could see another large model that combines video with actions. Anyone following these systems should look for Runway's full announcement to confirm the model's details, availability and any performance claims. Until then, the information here rests on a partial reshared post.

Hardware and robotics watchers may want to track whether this becomes a product, benchmark, or deployment signal.

Signal Strength 81% Technical label WATCH Public Interest 31 Category ROBOTS & HARDWARE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 0 Practical Impact Score 20 Novelty Interest Score 70 Consequence Score 22 Curiosity Score 48 Shareability Score 45

VQV surfaced this signal because it is recent, relevant to Robotics, connected to Scobleizer News Pulse (X).