Microsoft has updated its AI research tool, Copilot Researcher, to use models from both OpenAI and Anthropic. This move is seen as a sign that the future of AI may be multi-model. The new "Critique" layer uses Anthropic's Claude to review answers generated by OpenAI's model to improve accuracy and score 13.8% higher on the DRACO benchmark. Another new option, Model Council, allows users to see a side-by-side comparison of responses from different models. However, using multiple models on a single query can lead to increased costs and slower response times.