Development

A model learns jointly from images, video and audio into one representation

development2026-07-24

Claim

Black Forest Labs shipped FLUX 3, a model learning jointly from images, video and audio into one representation of reality, plus twenty-second native-audio video, with that backbone becoming a video-action model deployed at Audi for soft-body work at human reaction speed.

Reporting date: 2026-07-24 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to July 24, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to July 24, 2026

Actor

Evidence for

Supersedes

A tendon-driven hand hoists 55 pounds yet senses a tenth of a newton

Referenced by

Welcome to July 24, 2026

Cite or correct this record

Citation formatCitation text

A model learns jointly from images, video and audio into one representation
Innermost Loop KB — secondary record
Reporting date: 2026-07-24
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-07-24-one-representation-of-reality-across-image-video-and-audio
Claim: Black Forest Labs shipped FLUX 3, a model learning jointly from images, video and audio into one representation of reality, plus twenty-second native-audio video, with that backbone becoming a video-action model deployed at Audi for soft-body work at human reaction speed.
Attributed sources:
- Welcome to July 24, 2026 — https://theinnermostloop.substack.com/p/welcome-to-july-24-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.