[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-chatgpt-mac-computer-history-memory-en":3,"article-related-chatgpt-mac-computer-history-memory-en":29,"series-ai-agent-1ae1e1b4-ef77-411e-94d5-0f5fd70897d6":78},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":11},"1ae1e1b4-ef77-411e-94d5-0f5fd70897d6","chatgpt-mac-computer-history-memory-en","ChatGPT now remembers your Mac work history","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fchatgpt\">ChatGPT\u003C\u002Fa> can now remember recent Mac activity without using screenshots.\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fopenai.com\" target=\"_blank\" rel=\"noopener\">OpenAI\u003C\u002Fa> has added a memory feature to \u003Ca href=\"https:\u002F\u002Fchatgpt.com\" target=\"_blank\" rel=\"noopener\">ChatGPT\u003C\u002Fa> for the Mac that lets the assistant recall what you did on your computer. The new capability is meant to help users pick up where they left off, and it does that by storing computer history instead of relying on screen captures.\u003C\u002Fp>\u003Cp>The change matters because it moves ChatGPT from a chat tool that reacts to prompts into one that can remember context across sessions. That is useful for coding, research, and admin work, but it also raises obvious questions about what gets stored, where it lives, and who can see it.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>Item\u003C\u002Fth>\u003Cth>Detail\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>Product\u003C\u002Ftd>\u003Ctd>ChatGPT for Mac\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Feature\u003C\u002Ftd>\u003Ctd>Computer history memory\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Data source\u003C\u002Ftd>\u003Ctd>Recent Mac activity, without screenshots\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Vendor\u003C\u002Ftd>\u003Ctd>OpenAI\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Related concern\u003C\u002Ftd>\u003Ctd>Agent memory and privacy exposure\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>What OpenAI changed on the Mac\u003C\u002Fh2>\u003Cp>The headline feature is simple: ChatGPT can now remember what happened on your Mac and use that history later. Instead of depending on screenshot archives, the assistant keeps a memory of recent activity so it can answer follow-up questions with less setup.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786777367544-sddp.png\" alt=\"ChatGPT now remembers your Mac work history\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>That sounds small, but it changes the shape of the product. A chat assistant that remembers your last terminal command, document draft, or browser task can behave more like a working companion than a blank prompt box.\u003C\u002Fp>\u003Cp>This is also where the product gets more opinionated. If the assistant remembers your computer history, then the quality of its memory matters as much as the quality of its answers. A stale or incomplete memory can be worse than none at all.\u003C\u002Fp>\u003Cul>\u003Cli>It reduces the need to restate context every time you reopen ChatGPT.\u003C\u002Fli>\u003Cli>It can help with multi-step work across coding, writing, and research.\u003C\u002Fli>\u003Cli>It creates a new privacy surface because history is stored for later use.\u003C\u002Fli>\u003Cli>It changes how users judge trust, since memory is now part of the product.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Memory is useful, but it is also a security problem\u003C\u002Fh2>\u003Cp>\u003Ca href=\"\u002Ftag\u002Fagent\">Agent\u003C\u002Fa> memory has been one of the messiest problems in AI software. The more context a system keeps, the more damage a mistake can do. A model that remembers your last few actions can be helpful during normal work and dangerous if that memory leaks, gets misread, or is reused in the wrong place.\u003C\u002Fp>\u003Cp>That is why this story connects to a bigger debate in agent design. The more autonomy and memory you give a system, the more you need hard controls around data access, logging, and replay. Without those controls, “helpful” becomes “hard to audit” very quickly.\u003C\u002Fp>\u003Cblockquote>“The first rule of AI is to make sure that you’re not making decisions based on the wrong data.” — \u003Ca href=\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpeople\u002Fhorvitz\u002F\" target=\"_blank\" rel=\"noopener\">Eric Horvitz\u003C\u002Fa>\u003C\u002Fblockquote>\u003Cp>Horvitz’s line fits this feature well. If ChatGPT is remembering your Mac activity, then the assistant needs clean data boundaries and a clear memory model, or it risks building answers on partial or misleading context.\u003C\u002Fp>\u003Cp>For developers, the real question is not whether memory is useful. It clearly is. The question is whether the product exposes enough controls for people to inspect, delete, and limit what gets remembered.\u003C\u002Fp>\u003Ch2>How this compares with other AI desktop tools\u003C\u002Fh2>\u003Cp>ChatGPT is not the only assistant trying to become more persistent on the desktop. \u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002Fclaude\" target=\"_blank\" rel=\"noopener\">Anthropic’s Claude\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fwww.cursor.com\" target=\"_blank\" rel=\"noopener\">Cursor\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fwindows\u002Fcopilot\" target=\"_blank\" rel=\"noopener\">Microsoft Copilot\u003C\u002Fa> all push in the same direction: more context, less repeated prompting, and more work done from the desktop.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786777373735-qzez.png\" alt=\"ChatGPT now remembers your Mac work history\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>What differs is the memory model. Some tools lean on chat history, some on workspace files, and some on screenshots or local activity logs. \u003Ca href=\"\u002Ftag\u002Fopenai\">OpenAI\u003C\u002Fa>’s Mac approach is notable because it tries to preserve continuity without forcing users to depend on image capture.\u003C\u002Fp>\u003Cul>\u003Cli>\u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002Fclaude\" target=\"_blank\" rel=\"noopener\">Claude\u003C\u002Fa> focuses on conversation context and file-based workflows.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fwww.cursor.com\" target=\"_blank\" rel=\"noopener\">Cursor\u003C\u002Fa> keeps the center of gravity inside the code editor.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fwindows\u002Fcopilot\" target=\"_blank\" rel=\"noopener\">Copilot\u003C\u002Fa> is tied tightly to Microsoft’s desktop ecosystem.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fopenai.com\u002Fchatgpt\" target=\"_blank\" rel=\"noopener\">ChatGPT\u003C\u002Fa> is now trying to remember what you did on the Mac itself.\u003C\u002Fli>\u003C\u002Ful>\u003Cp>That comparison matters because memory is becoming a product differentiator. If two assistants can answer the same prompt, the one that remembers your prior work will feel faster and smarter, even if the underlying model quality is similar.\u003C\u002Fp>\u003Cp>But memory also changes the trust contract. Users may accept a little friction to keep data local or tightly scoped. They may not accept a system that remembers too much and explains too little.\u003C\u002Fp>\u003Ch2>What developers should watch next\u003C\u002Fh2>\u003Cp>The most important detail is how OpenAI exposes controls around this feature. If users can see what ChatGPT remembers, clear it quickly, and limit it to specific apps or sessions, the feature has a real chance of being useful. If those controls are buried, adoption will stall among security-conscious teams.\u003C\u002Fp>\u003Cp>Developers should also watch whether this memory layer becomes available beyond the Mac. If it does, the pressure to define consistent rules for retention, deletion, and auditability gets much higher. That is where product convenience meets enterprise risk.\u003C\u002Fp>\u003Cp>There is also a broader systems question here. \u003Ca href=\"\u002Ftag\u002Fai-agents\">AI agents\u003C\u002Fa> keep getting better at acting on our behalf, but they still need memory, identity, and permission boundaries that are much stricter than a normal chatbot. The companies that get those details right will earn trust faster than the ones that just add more context and hope for the best.\u003C\u002Fp>\u003Cp>For now, the practical takeaway is simple: if you use ChatGPT on a Mac, assume it is becoming more persistent, not less. The next useful feature may also be the one you want the most control over.\u003C\u002Fp>\u003Cp>As AI assistants move deeper into the desktop, the winners will be the tools that remember enough to help and expose enough controls to stay trustworthy.\u003C\u002Fp>","OpenAI’s ChatGPT can now recall recent Mac activity without screenshots, raising the bar for agent memory and privacy risk.","thenewstack.io","https:\u002F\u002Fthenewstack.io\u002Fopenai-chatgpt-computer-history\u002F",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786777367544-sddp.png","ai-agent","en","772d3194-0952-435e-a971-31fe65acc542",[17,18,19,20,21],"ChatGPT","OpenAI","Mac","memory","AI agents",[23,24,25],"ChatGPT on Mac can now remember recent computer activity without screenshots.","The feature improves continuity, but it adds new privacy and auditability concerns.","Memory is becoming a key differentiator across desktop AI assistants.",1,"2026-08-15T07:02:25.759069+00:00","2026-08-15T07:02:25.745+00:00",{"tags":30,"relatedLang":37,"relatedPosts":41},[31,33,35],{"name":18,"slug":32},"openai",{"name":17,"slug":34},"chatgpt",{"name":21,"slug":36},"ai-agents",{"id":15,"slug":38,"title":39,"language":40},"chatgpt-mac-computer-history-memory-zh","ChatGPT 會記住 Mac 工作歷史","zh",[42,48,54,60,66,72],{"id":43,"slug":44,"title":45,"cover_image":46,"image_url":46,"created_at":47,"category":13},"add7325b-6922-4d4f-941d-f7c716a48217","grok-bot-turns-browser-chores-into-cloud-work-en","Grok Bot turns browser chores into cloud work","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786757604668-vcyt.png","2026-08-15T01:33:02.708294+00:00",{"id":49,"slug":50,"title":51,"cover_image":52,"image_url":52,"created_at":53,"category":13},"10a73d21-d035-474d-9fd9-1a1dd5caa863","agent-plugins-100-turns-skills-into-folders-en","Agent Plugins 1.0.0 turns skills into folders","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786610024064-pe2a.png","2026-08-13T08:33:10.730688+00:00",{"id":55,"slug":56,"title":57,"cover_image":58,"image_url":58,"created_at":59,"category":13},"b77650c4-7664-4af1-8ff1-2e1b792cdd58","faitheyes-tool-faithful-vision-agents-en","FaithEyes lets you train tool-faithful vision agents","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786258993834-8aqq.png","2026-08-09T07:02:49.995282+00:00",{"id":61,"slug":62,"title":63,"cover_image":64,"image_url":64,"created_at":65,"category":13},"3491c99c-621c-40d3-bbd8-b4a73702fb42","connect-qwen-3-8-max-cli-agents-en","Connect Qwen 3.8 Max to CLI Agents","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786255373689-rrwa.png","2026-08-09T06:02:30.990794+00:00",{"id":67,"slug":68,"title":69,"cover_image":70,"image_url":70,"created_at":71,"category":13},"445ecce7-ea09-49f7-a7f4-88391eb1bbf3","fine-tune-small-llm-legal-labeling-en","Fine-tune a small LLM for legal labeling","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786150968314-7umc.png","2026-08-08T01:02:27.269166+00:00",{"id":73,"slug":74,"title":75,"cover_image":76,"image_url":76,"created_at":77,"category":13},"306b4d13-3911-4fcb-9f53-861fa5e9b430","sala-boosts-long-context-edge-ai-en","SALA Boosts Long Context on Edge AI","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1785765793459-52io.png","2026-08-03T14:02:45.076761+00:00",[79,84,89,94,99,104,109,114,119,124],{"id":80,"slug":81,"title":82,"created_at":83},"03db8de8-8dc2-4ac1-9cf7-898782efbb1f","anthropic-claude-ai-agent-task-automation-en","Anthropic's Claude AI Agent: A New Era of Task Automation","2026-03-25T16:25:06.513026+00:00",{"id":85,"slug":86,"title":87,"created_at":88},"045d1abc-190d-4594-8c95-91e2a26f0c5a","googles-2026-ai-agent-report-decoded-en","Google’s 2026 AI Agent Report, Decoded","2026-03-26T11:15:23.046616+00:00",{"id":90,"slug":91,"title":92,"created_at":93},"e64aba21-254b-4f93-aa21-837484bb52ec","kimi-k25-review-stronger-still-not-legend-en","Kimi K2.5 review: stronger, still not a legend","2026-03-27T07:15:55.385951+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"30dfb781-a1b2-4add-aebe-b3df40247c37","claude-code-controls-mac-desktop-en","Claude Code now controls your Mac desktop","2026-03-28T03:01:59.384091+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"254405b6-7833-4800-8e13-f5196deefbe6","cloudflare-100x-faster-ai-agent-sandbox-en","Cloudflare’s 100x Faster AI Agent Sandbox","2026-03-28T03:09:44.356437+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"04f29b7f-9b91-4306-89a7-97d725e6e1ba","openai-backs-isara-agent-swarm-bet-en","OpenAI backs Isara’s agent-swarm bet","2026-03-28T03:15:27.849766+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"3b0bf479-e4ae-4703-9666-721a7e0cdb91","openai-plan-automated-ai-researcher-en","OpenAI’s plan for an automated AI researcher","2026-03-28T03:17:42.312819+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"fe91bce0-b85d-4efa-a207-24ae9939c29f","harness-engineering-ai-agent-reliability-2026","Harness Engineering: From Bridle to Operating System, The Missing Link in AI Agent Reliability","2026-03-31T06:36:55.648751+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"7a09007d-820f-43b3-8607-8ad1bfcb94c8","mcp-explained-from-prompts-to-production-en","MCP Explained: From Prompts to Production","2026-04-01T09:24:40.089177+00:00",{"id":125,"slug":126,"title":127,"created_at":128},"116d5ee9-a4f1-4b5a-aac5-5d035dd22bbe","amazon-bedrock-agents-multi-agent-workflows-en","Amazon Bedrock Agents Gets Multi-Agent Workflows","2026-04-01T09:30:30.197685+00:00"]