OpenAI’s October 16 release notes announce parallel agents for GPT-6 Pro in ChatGPT’s chat tab. The company says multiple agents can work on different parts of a task, while users follow their progress in the conversation and open completed tasks to inspect each agent’s work. OpenAI also reports faster responses and improved use of plugins and tools; it provides no numerical speed comparison in this entry.
The update is rolling out to eligible Pro users. Availability in managed workspaces depends on workspace settings and rollout eligibility, so the announcement does not establish access for every account. It describes ChatGPT’s chat tab, rather than announcing a new Dots feature. That distinction matters when deciding where to start a task or looking for the new controls.
Editorial take: Parallel execution could help with work that separates cleanly, such as researching different options before assembling a comparison. The useful review point is the combined result: check that the pieces use compatible assumptions and that conclusions match their evidence. We have not tested this rollout or measured whether parallel work improves accuracy or completion time.