Morning Edition · Sunday, June 28, 2026
Open-Vocabulary Segmentation Reaches Production as Apps Build on Meta's SAM 3
Meta's promptable concept-segmentation model, which finds and tracks any specified object from a text prompt, is moving from benchmark tests into shipping consumer products.
Meta's Segment Anything Model 3 is an 848-million-parameter foundation model that detects, segments, and tracks objects from text prompts and visual prompts across images and video. Unlike its predecessor, SAM 3 can exhaustively find every…
Continue the AI Intelligence Brief
Track frontier labs, chips, export controls, model releases, regulation, and AI infrastructure.
- 5 AI intelligence signals a day
- Frontier labs, compute, and chips
- Model releases and AI infrastructure
- Source-grounded analysis with confidence labels
The Global Intelligence Brief stays free.
Part of a tracked trend
Open-Vocabulary, Promptable Vision Foundation Models
Vision foundation models shift to text-promptable, open-vocabulary detection, segmentation, and real-time tracking of arbitrary concepts, generalizing perception beyond fixed label sets across images and video and pushing open perception models toward production use.
More from this edition
- AI's First Revenue Census Puts Generative-AI Sales at $110 Billion, Above Infrastructure Depreciation
- Washington Orders Anthropic to Cut Foreign Access to Two Top Models, Citing a Narrow Jailbreak
- DeepSeek Open-Sources DSpark, Claiming Up to 4x Throughput on V4 via Speculative Decoding
- MirrorCode Benchmark Finds Frontier Models Can Rebuild Real Software From Scratch, Up to a Point
- EU Picks an Italian Startup to Build a 400-Billion-Parameter Open Model in 24 Languages
- Anthropic Asks Washington for Power to Block Dangerous Models, Plus $350 Million for Labor Fallout
- Alibaba Sues the Pentagon to Get Off Its Chinese-Military-Company List
- Anthropic Puts Claude Inside Slack as a Taggable Teammate With Shared Memory
- A Venture Investor Accuses AI Leaders of Using Doom Warnings as a Fundraising Tool
- Brain-to-Image Decoding Advances, and DeepMind's Hassabis Frames It as AI for Science
- Meta's Muse Spark Shows the Efficiency Turn in Frontier Models, and a Break From Open Weights