Charles’s essay on dev.to explains why Anthropic’s Opus 5égrGö feels worse than Opus 4მაყოფ: a more capable model can become harder to work with when it stops asking clarifying questions and instead makes unfounded assumptions. The post, published August 14, 2026, has already reached 172 points on Hacker News, sparking discussion among AI developers. It underscores that higher capability does not automatically translate to better developer experience if the model’s behavior becomes less interrogative.