aiqbench takeAI Products

Anthropic has unified Claude's chat and Cowork interfaces into a single persistent memory system, eliminating the need for redundant context re-entry across different usage modes. This architectural shift allows agents to maintain continuous project awareness while giving users direct control over their stored data, including sensitive topics which remain opt-in by default. The update represents a significant evolution in how LLM applications manage long-term state and user context without sacrificing privacy controls.

Sources coveringTechCrunch, Quantum Computing Report, The Verge, Slack Blog

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Claude Cowork finally remembers what you told the app in chat

TechCrunchAugust 25, 20263 min read

Anthropic is giving Claude a shared memory across chat and Cowork, so users no longer have to repeatedly brief the AI on projects, preferences, and other context.

A change to Claude’s memory system will eliminate one of the most annoying things about using agents — the constant need to rebrief the AI on things it already knows. On Tuesday, Anthropic announced it’s merging the memory system used by chat and Claude Cowork, which means that…

Excerpt shown under the publisher's RSS terms · 48 words · full text and figures are on the publisher's site

Read at TechCrunch ↗Ask about this article