Anthropic résout un problème d'ergonomie récurrent en unifiant la persistance des données. L'accès direct au registre de mémoire permet d'éditer ou purger les faits enregistrés par l'agent.
La fragmentation du contexte entre l'interface de conversation et l'agent d'exécution représentait une friction majeure dans l'utilisation quotidienne de Claude.
L'éditeur réorganise la mémoire de son assistant pour éviter la re-saisie d'informations lors du passage du chat aux actions automatisées. Le système met désormais à jour les sujets en temps réel durant les conversations et permet de lire, modifier ou supprimer chaque donnée enregistrée.
Impact concret
Les collaborateurs n'ont plus à réexpliquer les données de cadrage comme les effectifs ou les consignes lors du passage de la discussion à l'exécution de tâches dans Cowork.
Applications concrètes
Continuité de travail entre le brainstorming par tchat et la génération de livrables dans Cowork; contrôle manuel et suppression ciblée des informations mémorisées par l'assistant.
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 Claude will always remember what it learned in one area, even when you’re engaging with it in another. Anthropic is also exposing what Claude has retained in its memory, allowing users to read, edit, or delete information on any topic. Image Credits: Anthropic The update will improve the experience for Claude’s users as it will allow them to more seamlessly move between the research phase and taking action. Before, you may have developed ideas for projects over time while chatting with Claude, but when it came time to actually enact the changes, you’d have to start over by telling Cowork all the details. This was incredibly frustrating. The update makes Claude now feel like one continuous assistant, rather than two separate products under one roof. Anthropic offers an example of someone needing to draft an update for their manager or an agenda for a conference, where Cowork would already understand the references because of the past conversations about the matter at hand. For instance, it would know the headcount, city, and speakers at the conference, so you wouldn’t have to re-input that information. Image Credits: Anthropic In addition, Claude will now add topics to its memory as you chat, instead of summarizing a conversation when it ends. That makes it easier to move back and forth between chat and Cowork, as the new memories are more quickly updated and shared between the two experiences, even if the chat is ongoing. Anthropic says that, by default, Claude won’t store personal or sensitive information like your health data, race, ethnicity, religious beliefs, politics, gender identity, and more. However, users can opt to enable these things by toggling on “include sensitive topics in memory” if they prefer. The app will also notify users whenever a sensitive topic is saved in memory. However, the company says that Claude won’t ever save certain things, like government-issued ID and Social Security numbers, criminal history, immigration status, or other things that violate its acceptable use policy. The memory feature is enabled by default on Free, Pro, and Max plans across web, desktop, and mobile. On iOS and Android, users will need to update their app to the latest version. Topics AI , AI , Anthropic , Apps , Claude When you purchase through links in our articles, we may earn a small commission . This doesn’t affect our editorial independence. Sarah Perez Consumer News Editor Sarah has worked as a reporter for TechCrunch since August 2011. She joined the company after having previously spent over three years at ReadWriteWeb. Prior to her work as a reporter, Sarah worked in I.T. across a number of industries, including banking, retail and software. You can contact or verify outreach from Sarah by emailing sarahp@techcrunch.com or via encrypted message at sarahperez.01 on Signal. View Bio October 13 – 15 San Francisco In less than 48 hours, your chance to save up to $300 on your tickets will end! REGISTER NOW Most Popular Two years after launch, Walmart’s Flipkart is closing in on India’s quick-commerce leaders Jagmeet Singh Inherent, founded by DeepMind alumni, says its AI ‘teammate’ just outperformed Anthropic and OpenAI at replicating research Anna Heim Michael Polansky is training an AI model on skin that’s still alive Connie Loizos How AI accounting startup Rillet raised $100M and became a unicorn in 48 hours Dominic-Madori Davis Tesla’s solar roof is dead — here’s what went wrong Tim De Chant Oura faces lawsuit accusing it of misleading consumers about sleep-tracking accuracy Aisha Malik Home batteries are suddenly cheap and everywhere. Here’s why. Tim De Chant