How We Built Safety Into Muse | Meta AI Research
research.meta.ai · 4,025 words · saved by 1 readers
By going into detail about how Muse works under the hood, we hope to give you a sense of how — and how much — you can trust it in practice.
Today we launched Muse — our personal agent. We’ve been working on and using Muse ourselves since early 2026. As soon as we started using it, we saw the glimmers of real personal superintelligence — an agent that knows you, actually does things, works in the background, launches swarms of subagents, builds its own tools, and edits itself. It was also the first time we’d handed our inboxes, our calendars, and a shell to a piece of software and let it run unattended — which didn’t always work out as planned. Making this technology work for everyone requires careful design and engineering to…
saved by
related reading
- Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
- First Impression of Musembi-deepdives.com
- Claude Mythos Preview System Cardwww-cdn.anthropic.com
- ai.meta.com/static-resource/muse-spark-contemplating-safety-and-preparedness-report/ai.meta.com
- Introducing Muse Spark: Scaling Towards Personal Superintelligenceai.meta.com
- How we contain Claude across products \ Anthropicanthropic.com
- Lessons from Moltbook and OpenClaw: The Agentic Internet’s Trust Problem - Irregularirregular.com
- 2312.06942arxiv.org
- Introducing Muse Spark 1.1ai.meta.com
- Security incident disclosure — July 2026huggingface.co
- Arjun Virkarjunvirk.com
- Claude Mythos Preview System Cardwww-cdn.anthropic.com