GoKawiil
Tech News
Anthropic has given Claude Cowork the same memory system as Claude's chat interface, so tasks and context carry over between the two. Instead of summarizing chats after they end, Claude now logs topics to memory in real time, and users can view, edit or delete these entries under a Topics section in Memory settings. The feature is live for Free, Pro and Max users on web, desktop and mobile.
Anthropic announced it is merging the memory systems behind Claude's chat interface and its Cowork agent product, so information learned in one context carries over to the other. Users can now view, edit, or delete stored memories, and Claude will log details continuously during conversations rather than only summarizing at the end.
Anthropic has unified its memory feature so that Claude Cowork, its cloud-based task tool, now shares the same memory as Claude's chat interface. This means details from prior conversations carry over into Cowork tasks and vice versa, reducing the need to re-explain context. Sensitive topics like health or beliefs are excluded from memory by default but can be manually enabled in settings.
Anthropic now shares a single memory system between Claude and its Cowork tool, so context from past chats carries over automatically when switching between them. Claude also updates its memory in real time without needing explicit prompts, and users get new controls to view, edit, delete or pause stored memories in Settings.
Anthropic now lets Claude share memories between its chatbot interface and Cowork, its cloud-based computer-use agent, so context from regular chats carries into automated tasks and back. The update also adds a toggle letting users allow Claude to remember sensitive topics like health or politics, which are excluded by default, with notifications each time such a memory is stored.
Anthropic has merged the memory systems behind its Claude chatbot and Claude Cowork productivity tool, so information learned in one now carries over to the other automatically as users interact with either. Memory updates continuously during conversations and includes controls for handling sensitive data, while Claude Code remains unaffected by this change. Users can opt out of the shared memory feature if they prefer their sessions to stay isolated.
Ambient Context is a macOS menu bar utility that periodically reads the text of your active window through the accessibility API and appends it to a local, per-day markdown file. It's designed so tools like Claude Code or other agents can read that folder later to answer questions about your work history or draft summaries such as standups.
A developer released a Claude Code plugin skill that pulls every highlight from a Kindle book's notebook page, including ones Amazon's export feature truncates or hides entirely due to an undocumented export cap. It reconstructs the missing text by cross-referencing the Mac Kindle app's synced annotation positions and the Cloud Reader's rendered pages, producing one combined, verbatim Markdown file with location citations.
An independent game developer built Wyvern using a self-organized workforce of 50-60 AI agents, led by 18 long-running Claude Fable instances acting as department heads, supported by headless Claude Sol and Opus fleets for implementation and review. The setup burns roughly $122,000 a month in equivalent API usage, though the developer pays only about $5,000 out of pocket by exploiting Claude Max's flat-rate individual pricing across 21 accounts, running everything on a $25,000 secondhand 512GB Mac Studio.
Anthropic revised Claude Tag, its Slack-based agent, so it now analyzes entire conversation threads instead of assessing messages individually. The company says this context upgrade makes the agent about 30% more accurate at judging when to jump into a discussion unprompted—and when to stay silent. Executive Scott White frames this as part of a broader push toward 'multiplayer AI,' where Claude operates as a shared organizational resource rather than a private chatbot.
AI chatbots like Gemini, ChatGPT and Claude often store user conversations on company servers and use that data by default to train future AI models. Users can disable this training option and delete past activity, though turning off tracking does not automatically erase previously stored data. For Gemini specifically, users must disable both Google's Web & App Activity and Gemini's own Activity setting, then manually delete existing records.
Anthropic published a terminology guide clarifying that an 'agent system' is not the same as a 'model.' It breaks the stack into three parts: the model (like Sonnet or Opus), the inference service that runs it (like AWS Bedrock or Anthropic's API), and the harness, the interface layer such as Claude Desktop or Claude CLI that manages tools and context.