ChatGPT의 새로운 전이중(full-duplex) 음성, 사고 처리를 GPT-5.5에 위임
OpenAI가 동시에 듣고 말하는 전이중(full-duplex) 음성 모델 GPT-Live를 출시했으며, 지능 격차를 줄이기 위해 추론 작업은 백그라운드의 GPT-5.5에 위임합니다.
openai announced gpt-live, a new voice mode that uses full-duplex architecture to listen and speak simultaneously, mimicking human conversation patterns with interruptions and backchanneling. unlike previous versions, the model offloads web searches and complex reasoning to the gpt-5.5 model in the background, a move that boosts performance on the browsecomp benchmark from 0.7% to 75.2%. the update is available immediately on ios, android, and web for paying and free users, with api access planned for the future, signaling a shift toward multi-model agent architectures that separate conversational flow from cognitive processing.