from Microsoft Co-pilot is getting even better at searching with a new feature that combines the power of OpenAI’s ChatGPT and Anthropic’s Claude. In a blog post announcing Co-pilot CoworkAfter the availability of Microsoft 356 Copilot, Microsoft launched the Critical feature which will be used in the Researcher tool of Microsoft 356 Copilot. Unlike standard Copilot, Researcher is designed to tackle more complex, multi-step tasks.
Now, Researcher gets even better at this with the Critical feature that uses GPT responses, which are then refined by Claude. In a blog post, Microsoft said that “this architecture creates a powerful feedback loop that delivers higher quality results in terms of factual accuracy, analytical breadth, and presentation,” adding that the researcher’s process is similar to what you see in “academic and professional research settings.” Microsoft says the upgrade scores are slightly higher (compared to the most recent Perplexity Deep Research models) on the Deep Research Accuracy, Completeness, and Objectivity benchmark. On its own, Anthropic has a Search function who can call on several Claude agents to provide a complete response to more complex requests.
If you prefer to conduct research with a little more autonomy, Microsoft has also added the Model Council feature, available as an alternative option for Researcher. With Model Council, you’ll get side-by-side answers from Anthropic and OpenAI, with a report that shows where models agree and disagree. Both features are currently available in the Microsoft 365 Copilot Frontier program, which serves as an early access space to the company’s AI innovations.
This article was originally published on Engadget at https://www.engadget.com/ai/microsofts-research-assistant-can-now-use-multiple-ai-models-simultaneously-154558628.html?src=rss
