OpenAI adds GPT-6.1 Terra…Dots utilizes models per task
Original headline오픈AI, GPT-6.1 Terra 추가…Dots 작업별 모델 활용
Not investment advice. Muhabbit scores how much a story may matter, not which way to trade.
OpenAI added GPT-6.1 Terra to Dots, its always-on AI agent that can route different parts of a task to different models. Dots, unveiled September 29, continues working between user requests by drawing on connected apps and its own cloud computer, and OpenAI held a DevDay Exchange event in London on November 3. The agent's background research feature scans permitted apps for relevant context, with OpenAI saying access is restricted to read-only. Disconnecting an app does not remove information already absorbed into Dots' context, limiting users' control over what the agent remembers. The update signals OpenAI's push toward persistent, multi-model agents that act continuously rather than per prompt, and users will be watching how memory management and app-level permissions evolve.
Muhabbit's AI wrote this summary in its own words from TokenPost's report and translated it from Korean. It can get details wrong, so check the source.
Named in this story
Dots, OpenAI, GPT-6.1 Terra, DevDay Exchange, London