AI
Building Visual Intelligence — Andreas Blattmann & Dustin Podell, Black Forest Labs
Publication: Latent Space: The AI Engineer Podcast
Author: Not available in collected metadata
Source published: 16/11/2026, 21:27:06 UTC
Briefing created: 17/11/2026, 00:16:14 UTC
Based on the episode description, not a full transcript. Source evidence retrieved 17/11/2026, 00:12:24 UTC.
Briefings
Black Forest Labs' FLUX 3 model was trained on multimodal data combining images, video, and audio. Andreas Blattmann and Dustin Podell discussed the technical approach in a podcast episode. The episode begins by describing a moving camera capturing the far side of an object.
Key points
- FLUX 3 was trained on multimodal data combining images, video, and audio.
- The podcast episode features Andreas Blattmann and Dustin Podell discussing the training methodology.
Context
This podcast episode features Andreas Blattmann and Dustin Podell from Black Forest Labs discussing the technical approach behind training FLUX 3 on multimodal data.
Limitations
The provided evidence is a truncated podcast transcript with no specific dates, locations, or quantitative results. The content is limited to the initial description of the camera and the introduction of the speakers.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 17/11/2026, 00:16:14 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeigl3apoah7awovzzbzas24hxn4xczlo57uwu4xgzpwhtveenadto4