h.sHamid Samir
All stories

Report describes Dots as persistent ChatGPT agents with cloud computers

A report says OpenAI’s Dots agents keep working after ChatGPT closes, with cloud computers and app access. Actions require approval, and the account notes error risks.

A report says OpenAI has launched Dots, persistent ChatGPT agents with their own cloud computers and browsers that can keep working after the user closes the app.

According to the account, Dots run on GPT-6 Astra, can access more than 4,000 apps, and can research connected services while users are away before taking actions with their approval. It says saved logins can be used without exposing passwords to the model, while password changes remain human-only.

The same report says OpenAI cautions that agents can make mistakes and describes an earlier incident in which research agents accidentally posted 53 user-uploaded images online. It also presents Meta’s Muse as a similar approach to assistants with computers, memory and app access. These details are reported claims, not independently verified by the available material.