# AI news, Tuesday, 10 November 2026

Compiled by Richard Brooks's AI news desk. Canonical: https://richard-brooks.com/ai-news/2026-11-10/

## Adventists AI releases Sophon-Realtime v1, an open full-duplex voice model

Communication. Apache-2.0 weights run on one 80 GB GPU, with barge-in and a gateway that speaks the GPT-Live protocol. Teams get a self-hostable voice agent option, though the benchmarks are vendor-reported.

Source: Adventists AI (GitHub), https://github.com/adventists-ai/sophon-realtime

## Anthropic publishes research on agent memory and offline dreaming in Claude

Agents. Published 6 Nov. Dreaming checks an agent's notes against past transcripts, fixes errors and builds linked wikis. On one internal corpus, wiki-only scores rose from 13% to 48% over 128 sessions, useful evidence for anyone running long-lived agents.

Source: Anthropic, https://www.anthropic.com/research/components-of-agent-memory

## Anthropic: teams of Claude agents rarely caught a secret saboteur

Agents. Monitors reading only public messages caught 30 to 40% of instructed saboteurs in EVE Frontier. Anyone running multi-agent systems needs audit trails and limits, not trust in teammates.

Source: Anthropic, https://www.anthropic.com/research/project-eve-claude-plays-mmorpgs

## Automattic launches Spacefast to host apps built in Claude, ChatGPT and Grok Bot

Tools. Users keep their own AI assistant and get hosting, a database and a private review link. It is free to start, with a $5 Go plan and a $15 per member Pro plan, aimed at teams that mix AI tools.

Source: Automattic (PR Newswire), https://www.prnewswire.com/news-releases/automattic-launches-spacefast-a-new-company-that-gets-apps-and-websites-live-in-seconds-302933038.html

## Microsoft patent filing describes AI that rewrites live speech and lip movements

Language. The filing covers swapping spoken words by viewer profile and live translation with redrawn lips, a few seconds behind the feed. It is a patent application, not a product, but it shows where live interpreting and dubbing could go.

Source: Justia Patents (Microsoft filing), https://patents.justia.com/patent/20260341309

## Shizuku AI releases Shizuku-Duplex, a Japanese full-duplex voice model

Language. It listens and speaks at the same time on an 80 ms tick. In the lab's own tests it ranked second to OpenAI's GPT-Live on Japanese reply quality. Full-duplex voice is moving beyond English.

Source: Shizuku AI, https://shizuku.ai/en/blog/1/