OpenAI's dots agent can now connect to multiple local computers and split tasks across them
OpenAI announced on November 9 (US time) that its always-on agent tool dots can now connect to multiple local computers. Each machine can be given a separate task. The feature is available to Pro, Business Premium and Enterprise plan users in eligible regions.
OpenAI announced on November 9 (US time) that dots, its always-on agent tool, can now connect to multiple local computers and assign a different task to each one. The news was reported in Japanese by ITmedia AI+ on November 10.
What changed
dots could already operate computers in the cloud, and it could also be given control of a user's own local computer. With this update, several local computers can be connected at once, so the work can be divided among them.
OpenAI gave three example uses:
- While the user develops an iOS app on a first Mac, a second Mac tests the changes in Xcode and sends the user screenshots of the test screen.
- The user prepares a laptop and a machine with an older SDK, runs the same test on both, and compares the results.
- A second computer runs UI click tests while the user keeps working freely on the first computer.
Background on dots
OpenAI announced dots in September as an always-on agent tool. It is built on the company's GPT-6 Astra and GPT-6.1 Terra models.
Availability
The feature is offered to users on the Pro, Business Premium and Enterprise plans in eligible regions. According to OpenAI's announcement, Japan ranks second among countries by number of dots users. OpenAI posted the announcement on X.
What this means
Until now, dots could drive either a cloud computer or a single local one. Multiple local connections let one instruction spread across several of a user's own machines, so each machine can run a separate job.
The examples OpenAI chose point to two uses. One is running tests on a second machine while the user keeps working on the first. The other is running the same test on machines with different setups, such as one with an older SDK, and comparing the results. In the iOS example, the agent also sends the user screenshots of the test screen from the second Mac.
Related Articles
Google Antigravity adds Knowledge Work interface for non-coding tasks, with the same agent underneath
Google is rolling out a Knowledge Work user experience in Antigravity, designed for research, data analysis, documents and presentations. The underlying agent is unchanged; the interface hides developer controls and uses plain-language permission prompts. Google says tens of thousands of Googlers outside software engineering use Antigravity weekly.
Qianwen Office 2.0 adds "Collaboration" so teams and Agents work in one shared space
Qianwen Office (千问办公) released version 2.0 on November 9, its largest upgrade in the three months since launch. The headline feature, "Collaboration," puts multiple people and digital employees in one shared workspace, and all new features are live in the client.
OpenAI introduces BioBasicsBench, a 100-task benchmark for AI agents in everyday wet-lab science
OpenAI has introduced BioBasicsBench, a benchmark of 100 tasks. It measures how well AI agents interpret raw experimental data and handle everyday wet-lab science.
Google Gemini adds 'Memory summary' to view, edit and delete what the app remembers about you
Google is rolling out a "Memory summary" in the Gemini app that lists what Gemini Apps understands about a user and lets them edit or delete it. Per 9to5Google, it is available to Google AI subscribers in US English with Keep Activity and Memory enabled.
Comments
Loading...