announced<\/a> that Claude and Cowork now share a memory, meaning that what Claude remembers about users is also available to Cowork. That\u2019s a two-way street: Memories generated through users\u2019 interactions with Cowork will also be available to the regular Claude chatbot.\u00a0<\/p>\nServices like Claude are able to store information about users, like what they\u2019re interested in, the names of their friends, family members, and coworkers, or almost anything else that\u2019s mentioned in the course of a conversation. Those memories are used to contextualize later responses so that Claude isn\u2019t answering from a blank slate every time a user chats.\u00a0<\/p>\n
As Anthropic explains in the announcement, memories are particularly helpful for work tasks of the type that Cowork is designed to perform. Cowork is a lot like Claude Code in that it\u2019s designed to automate manual work tasks, but in this case it\u2019s not about software development and is instead about everything else professionals deal with on a daily basis, like writing a report from a spreadsheet, creating a presentation from said report, or what have you. Y\u2019know – work.\u00a0<\/p>\n
\u201cAsk Cowork to draft an update for your manager, and it already knows who that is and how she likes updates written,\u201d Anthropic offers as one use of the new shared memory. As other examples, Anthropic posits brainstorming a conference agenda with Claude Chat and having Cowork know all about the event as it builds budget and logistics documents, or having to define once how a team likes metrics presented in a Claude chat and relying on Cowork to remember that format every quarter as you force it to do the work an intern used to have to be trusted to whip up.\u00a0<\/p>\n
It\u2019s worth noting that Claude Code\u2019s memory is staying separate, Anthropic told us. The company also mentioned it had nothing to share about the future of Claude Code\u2019s memory and whether it\u2019d join the hive in the future.\u00a0<\/p>\n
As for how Claude and Cowork create their shared memories, that\u2019s changing, too, Anthropic explained in the announcement. Whereas the pair previously created memories by reviewing a conversation at its conclusion, memories are now created on the fly during chats.<\/p>\n
Memory generation is on by default for users on free, Pro, and Max tiers (Cowork isn\u2019t available on Free accounts, though), but Anthropic said it doesn\u2019t remember \u201csensitive\u201d things without users opting to allow those to be stored in memory. Sensitive topics include things related to health, ethnicity, religious beliefs, politics, gender identity, and the like, though adding those to memory can be enabled if users so choose. Cowork will know those things too, mind you, and Anthropic told us there\u2019s no option to separate Claude Chat and Cowork\u2019s memories since they now use a shared system.<\/p>\n
An Anthropic spokesperson explained that the only way to keep Claude Chat and Cowork memories separate is to use different accounts. Other options, we\u2019re told, are to entirely pause Claude\u2019s ability to remember stuff, use incognito chats for conversations users don’t want remembered, or manually prune Claude\u2019s memory to get rid of individual topics.\u00a0<\/p>\n
The new shared memory is available from Tuesday; for Team and Enterprise customers, admins control whether memory is available, so if any of those great business features mentioned above sound useful, you may have to call IT and have them enable it. \u00ae<\/p>\n","protected":false},"excerpt":{"rendered":"ai and ml\u00a0 Shared memory is live, with no option to separate it between services, Anthropic tells us;…\n","protected":false},"author":2,"featured_media":749765,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-749764","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/749764","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=749764"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/749764\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/749765"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=749764"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=749764"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=749764"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}