GitHub Copilot public preview adds desktop screen control on macOS and Windows
GitHub released a public preview of Computer Use for Copilot CLI and the Copilot app on October 1. The feature lets the assistant read screen content and perform clicks, typing, scrolling, and drag operations across macOS and Windows applications, including software that lacks APIs. It is disabled by default and requires user approval per application.
Key points
- GitHub Copilot Computer Use public preview operates desktop apps on macOS and Windows
- Microsoft streaming transcription returns mid-utterance results with no SLA for preview
- ELYZA launches RSI Research org and two LLM-jp-4 models; self-improvement still a research goal
Microsoft also announced three voice models on October 1: MAI-Transcribe-2-Streaming, MAI-Voice-2.1, and MAI-Voice-2.1-Flash. The streaming transcription returns intermediate results mid-utterance and carries no SLA for the public preview; Microsoft says it is not recommended for production use.
ELYZA announced the ELYZA RSI Research organization on October 2, focused on AI-driven AI development. The lab released two models based on LLM-jp-4 but states that recursive self-improvement remains a research target, not an achieved result.
Model page: MAI-Transcribe-2-Streaming →
GitHub Copilot to Operate PC Screens—Progress in Voice AI and Domestic Autonomous Improvement Research [10/3 AI News]
note.com · 3 October 2026
Loading the full article…
This text was published by note.com and written by MOMO AI観測所. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Gemini may delete existing text when asked to append, author reports · 1 src
- Google's Gemini outperforms ChatGPT and Claude as Android assistant · 1 src
- Meta launches Muse AI agent in Mexico, first in Latin America · 11 src
- Meta rolls out real-time voice and expressive avatars for Muse AI in the US · 7 src
- Meta improves Muse and Meta AI with Active Memory and Active Focus · 2 src
Comments
via GitHub Discussions