New “imagination models” claim computer-use learning from 18 years of video
joemeno · x · 2026-07-25
A quoted post announces a new foundation-model architecture called “imagination models” and says its first model, Photon-1, learned computer use from 18 years of screen-recording video without action labels.
- The core claim is a new architecture designed for learning from internet-scale video.
- Photon-1 reportedly learned to operate a computer by watching massive screen recordings rather than paired action data.
- The post frames the result as a foundation-model breakthrough, not just a product demo.
Related event: Photon-1 Learns Computer Operation from 18 Years of Unlabeled Video(4 posts)→
More from Research
- Eric Topol and Derya Unutmaz clash over extrapolating GPT-4 study findings to frontier models — DeryaTR_ · 2026-10-27
- Reasoning models can barely control their chain of thought, paper finds — tomekkorbak · 2026-10-27
- New paper: LLM data schedules and learning rate schedules should be co-designed — jasondeanlee · 2026-10-27
- What makes research get adopted: important problems, proper evals, and usability — srchvrs · 2026-10-27
- First-week PhD student lands ARR Area Chair role, exposing peer-review quirks — anmarasovic · 2026-10-27
- EMNLP keynote: industry does read academic NLP papers, it just rarely credits them — srchvrs · 2026-10-27