copilot

Microsoft announced on Monday the launch of two new features for Copilot Researcher—Critique and Council—combining OpenAI's GPT with Anthropic's Claude for the same research task.Critique adopts a sequential collaboration model: GPT is responsible for planning the research, retrieving information, and generating the first draft, while Claude serves as a strict reviewer, checking the accuracy of facts and the quality of citations; Council allows both models to independently generate reports in parallel, with a third referee model comparing differences and summarizing discrepancies.In the DRACO benchmark test covering 100 complex research tasks across 10 fields including healthcare, law, and technology, Copilot equipped with Critique scored 57.4 points, leading the second place by nearly 14%, far surpassing Claude Opus running alone with a score of 42.7 points.

ChainCatcher news, according to sources, Microsoft has been working to increase both internal and third-party artificial intelligence models to support its flagship AI product Microsoft 365 Copilot, diversifying the existing OpenAI foundational technology and reducing costs.Microsoft is a major supporter of OpenAI, and this time Microsoft is seeking to reduce its reliance on the AI startup, which is different from the way Microsoft has boasted about its access to OpenAI models in recent years.Sources say that in addition to training its own smaller models (including the latest Phi-4), Microsoft is also working to customize other open models to make 365 Copilot faster and more efficient. It is reported that the aim of this move is to lower the costs of running 365 Copilot and potentially pass the savings on to end customers.