Muse Spaces; BioBasicsBench; Claude agent memory
Meta lets Muse build persistent mini-apps from a prompt; OpenAI scores agents on raw wet-lab data; Anthropic explains dreaming as the offline pass that keeps agent memory honest.
Show
- MetaNewsAgentsMeta launches Spaces: custom mini-apps Muse builds from a descriptionDescribe a planner, tracker or hub and Muse builds it into the app, with tabs you can pin or schedule and connected apps that keep it updated in the background. Available everywhere Muse is.
- OpenAINewsAgentsOpenAI introduces BioBasicsBench for AI agents on wet-lab analysis100 tasks from real Ligo experiments test whether agents can read raw gels, plates and instrument data, catch errors and refuse unsupported conclusions. GPT-6 Astra scores 66.7% at xhigh vs 43.8% for GPT-5.6 Sol.
- Anthropic EngineeringBlogAgentsAnthropic on agent memory: dreaming to correct, organize and preload notesEngineering write-up of how Claude keeps experience across sessions, and how offline "dreaming" fixes bad notes, builds wiki-style memory and decides what to load into the next session.