Claude’s Cowork feature now recalls your past chat instructions
Anthropic’s update to Claude’s memory system removes a major friction point in using AI agents: the repetitive need to re-explain context that the AI already retains. By merging the memory architectures of standard chat and Claude Cowork, Claude now maintains continuity across all interactions, remembering insights from one session even when switching to another.
Users can now view, edit, or delete any information stored in Claude’s memory, ensuring full transparency and control over what the AI retains.

Image Credits:Anthropic
This enhancement streamlines the workflow between research and execution, allowing users to transition seamlessly from brainstorming to action without losing context.
Previously, users might have developed project ideas through casual chats with Claude, only to face the frustration of restarting from scratch when switching to Cowork to implement those ideas. This update resolves that disconnect, making Claude feel like a single, cohesive assistant rather than disjointed tools.
For example, if you are drafting a manager update or a conference agenda, Cowork now leverages past conversations to automatically understand relevant context. It retains key details like headcount, location, and speaker lists, eliminating the need to re-enter this information manually.

Image Credits:Anthropic
Claude now updates its memory in real-time as you chat, rather than waiting for a conversation to end. This ensures that new insights are instantly shared between chat and Cowork, facilitating smoother transitions even during active discussions.
By default, Claude excludes sensitive personal data from memory, such as health records, race, ethnicity, religious beliefs, political views, and gender identity. Users can opt to include these topics by enabling the “include sensitive topics in memory” setting, and the app will notify them whenever such data is stored.
Strictly prohibited from being saved are government-issued IDs, Social Security numbers, criminal history, immigration status, and any other information violating Anthropic’s acceptable use policy.
This memory feature is enabled by default for Free, Pro, and Max subscribers on web, desktop, and mobile platforms. iOS and Android users must update their apps to the latest version to access these improvements.
Related article
Anthropic launches Opus 5
Anthropic unveiled Opus 5 on Friday, the latest iteration of its flagship model. Although smaller than Fable 5, this version offers lower costs and fewer restrictions, making it the preferred choice for most applications.Notably, Opus 5 surpasses Fab
Andreessen-backed Vals Targets AI Benchmarking Leadership
Benchmarking has become the industry standard for how AI companies validate their models’ capabilities, leverage favorable metrics to differentiate from competitors, and market their superiority. In short, strong benchmark results almost always trans
Apple Exec John Ternus Calls iPhone Best AI Device
Apple’s incoming CEO John Ternus clarified the company’s AI strategy during Wednesday’s Surprise and Shine event, asserting that the iPhone is already the premier AI device and prioritizing user data privacy over competitors.As Ternus succeeds Tim Co
Related Special Topic Recommendations
Comments (0)
0/500
Anthropic’s update to Claude’s memory system removes a major friction point in using AI agents: the repetitive need to re-explain context that the AI already retains. By merging the memory architectures of standard chat and Claude Cowork, Claude now maintains continuity across all interactions, remembering insights from one session even when switching to another.
Users can now view, edit, or delete any information stored in Claude’s memory, ensuring full transparency and control over what the AI retains.

Image Credits:Anthropic
This enhancement streamlines the workflow between research and execution, allowing users to transition seamlessly from brainstorming to action without losing context.
Previously, users might have developed project ideas through casual chats with Claude, only to face the frustration of restarting from scratch when switching to Cowork to implement those ideas. This update resolves that disconnect, making Claude feel like a single, cohesive assistant rather than disjointed tools.
For example, if you are drafting a manager update or a conference agenda, Cowork now leverages past conversations to automatically understand relevant context. It retains key details like headcount, location, and speaker lists, eliminating the need to re-enter this information manually.

Image Credits:Anthropic
Claude now updates its memory in real-time as you chat, rather than waiting for a conversation to end. This ensures that new insights are instantly shared between chat and Cowork, facilitating smoother transitions even during active discussions.
By default, Claude excludes sensitive personal data from memory, such as health records, race, ethnicity, religious beliefs, political views, and gender identity. Users can opt to include these topics by enabling the “include sensitive topics in memory” setting, and the app will notify them whenever such data is stored.
Strictly prohibited from being saved are government-issued IDs, Social Security numbers, criminal history, immigration status, and any other information violating Anthropic’s acceptable use policy.
This memory feature is enabled by default for Free, Pro, and Max subscribers on web, desktop, and mobile platforms. iOS and Android users must update their apps to the latest version to access these improvements.
Anthropic launches Opus 5
Anthropic unveiled Opus 5 on Friday, the latest iteration of its flagship model. Although smaller than Fable 5, this version offers lower costs and fewer restrictions, making it the preferred choice for most applications.Notably, Opus 5 surpasses Fab
Andreessen-backed Vals Targets AI Benchmarking Leadership
Benchmarking has become the industry standard for how AI companies validate their models’ capabilities, leverage favorable metrics to differentiate from competitors, and market their superiority. In short, strong benchmark results almost always trans
Apple Exec John Ternus Calls iPhone Best AI Device
Apple’s incoming CEO John Ternus clarified the company’s AI strategy during Wednesday’s Surprise and Shine event, asserting that the iPhone is already the premier AI device and prioritizing user data privacy over competitors.As Ternus succeeds Tim Co





Home






