Anthropic is reportedly developing a model that can infer what users want from incomplete instructions. According to The Information , a person who tested the unreleased model described stronger reasoning and intuition than the company’s current lineup. In the report’s example, a developer asks for a bug fix, and the model identifies a broader class of related problems and asks whether to address them too. Anthropic hasn’t confirmed a release date or model family and what still remains unclear is whether the model can distinguish between an incomplete request and work a developer deliberately...

Source: The New Stack