OpenAI has launched a new feature for its Codex coding tool, called Chronicle. According to the AI startup, Chronicle will create memories as you work with the platform. The AI can then better understand your prompts and do your work, without needing context every time.<\/p>\n
OpenAI CEO Sam Altman believes that this feature makes the process so easy, that he compared it to telepathy. He wrote on X, \u201cThe internal working name for this was \u2018telepathy, and it feels like it.\u201d<\/p>\n
Sam Altman says using Chronicle with Codex is like telepathy.\n<\/p>\n
Thibault ‘Tibo’ Sottiaux, the chief of Codex, claimed that while Chronicle consumes a lot of tokens \u2013 the unit measurement used for AI \u2013 at the moment, it can change the way you use Codex. He wrote, \u201cThis is early and consumes quite a bit of tokens, but it has changed how I and many folks at OpenAI use Codex.\u201d<\/p>\n
Codex chief Tibo has warned users that Chronicle can consume a lot of tokens in its current state.\n<\/p>\n
Codex can now remember your work<\/p>\n
Chronicle is designed to build memories of the work you do on Codex. The AI will create these memories based on the context on your screen. These memories can then be accessed by Codex to do tasks for you without asking you for context every time.<\/p>\n
That is, if you started working on a new project one day, the next day you can simply tell Codex to do something on \u201cthis\u201d or \u201cthat\u201d again. The AI will then continue working on the same project as it accesses Chronicle for memories.<\/p>\n
OpenAI says that now you don\u2019t have to write long prompts just to give context to the AI. The company wrote in a blog post, \u201cNo need to carefully craft your context and start from zero. Chronicle lets Codex fill in the gaps in your context.\u201d<\/p>\n
This feature aims to save time and effort for users by enhancing Codex’s understanding of their work habits.<\/p>\n
What about privacy?<\/p>\n
Chronicle builds memories from what it can see on your screen. According to OpenAI, the \u201cscreen captures are stored temporarily on device to generate memories\u2014also stored on device.\u201d<\/p>\n
Users can also inspect or edit memories. In case you don\u2019t want to use Chronicle, OpenAI states that it can be paused or disabled at any time from Codex’s menu bar.<\/p>\n
How to use Chronicle on Codex?<\/p>\n
This feature is currently available as an opt-in research preview for ChatGPT Pro subscribers on macOS, although it is not yet accessible in the EU, UK, and Switzerland.<\/p>\n
To enable Chronicle, you need to turn it on in the Memories setting page of the Codex app. Users also need to grant macOS Screen Recording and Accessibility permissions.<\/p>\n
– Ends<\/p>\n
Published By: <\/p>\n
Armaan Agarwal<\/p>\n
Published On: <\/p>\n
Apr 21, 2026 12:15 IST<\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI has launched a new feature for its Codex coding tool, called Chronicle. According to the AI startup,…\n","protected":false},"author":2,"featured_media":9743,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[8350,8356,8342,8352,8346,8355,8341,8353,2317,8348,8354,8345,157,8347,8351,508,370,8349,8343,8344],"class_list":{"0":"post-9742","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-openai","8":"tag-ai-coding-tool","9":"tag-ai-context-understanding","10":"tag-ai-memory","11":"tag-ai-project-memory","12":"tag-chatgpt-pro","13":"tag-chatgpt-pro-macos","14":"tag-chronicle","15":"tag-chronicle-privacy","16":"tag-codex","17":"tag-codex-memories","18":"tag-codex-opt-in-feature","19":"tag-macos","20":"tag-openai","21":"tag-openai-codex-chronicle-feature","22":"tag-openai-codex-updates","23":"tag-privacy","24":"tag-sam-altman","25":"tag-sam-altman-telepathy","26":"tag-telepathy","27":"tag-tokens"},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/9742","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=9742"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/9742\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/9743"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=9742"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=9742"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=9742"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}