The creator of Claude Code's prompting advice? Talk to your AI like a coworker (www.businessinsider.com)

Boris Cherny, the creator of Claude Code at Anthropic, has announced a significant shift in how users should interact with AI models. In a recent X post, he asserted that traditional "prompt engineering" is becoming obsolete as AI models, like Claude, have advanced in their understanding and performance. Cherny encourages users to engage with AI as they would with a coworker, emphasizing a more natural and straightforward approach to prompting. He suggests providing three key pieces of information: the task, the desired level of effort, and the method for verifying success. This change is noteworthy for the AI/ML community as it indicates a maturation of AI capabilities, allowing for simpler user interactions. Cherny demonstrated his approach with a casual prompt for Claude to create a visual artifact based on a podcast episode, illustrating that a conversational tone can elicit impressive results. His request included an aspect still open to interpretation—whether to use watercolor effects—highlighting the model’s ability to exercise creative judgment. This evolution in prompting philosophy not only streamlines user experience but also showcases the growing sophistication of AI, as seen in the watercolors generated by Claude, which reflect high-quality aesthetics comparable to professional data visualizations.