Amanda Askell, a member of Anthropic’s technical team and a trained philosopher, has shared her insights on crafting effective AI prompts, drawing on her academic background in philosophy to highlight the importance of clarity and precision. With a degree from Oxford and New York University, Askell brings a unique perspective to the art of prompting, emphasizing that the ability to communicate ideas clearly is just as vital in human-AI interaction as it is in philosophical discourse. In a recent episode of Anthropic’s "Ask Me Anything" podcast, Askell explained that mastering prompt engineering requires both experimentation and careful thought. “It is really hard to distill what is going on because one thing is just like a willingness to interact with the models a lot and to really look at output after output,” she said. She stressed the value of being highly experimental—testing different phrasings, structures, and levels of detail to see what yields the best results. But beyond trial and error, her philosophical training has played a key role in shaping her approach. “This is where I actually do think philosophy can actually be useful for prompting in a way because, like, a lot of my job is just being like I try and explain some issue or concern or thought that I'm having to the model as clearly as possible,” she said. This focus on precision and clarity helps not only improve the quality of prompts but also deepens understanding of how AI models process information. Anthropic itself has underscored this principle in its “Prompt Engineering Overview,” published in July, which advises users to think of its chatbot, Claude, as “a brilliant, but very new employee (with amnesia) who needs explicit instructions.” The company notes that Claude lacks context about personal preferences, writing styles, or internal guidelines. “The more precisely you explain what you want, the better Claude's response will be,” the guide states. This idea aligns with comments from veteran venture capitalist Marc Andreessen, who recently described AI as a “thought partner.” He emphasized that the real power of AI lies not just in its ability to respond, but in the quality of the questions asked. “Part of the art of AI is what questions to ask it,” he said. As the demand for skilled AI interaction grows, so does the value of prompt engineering. According to levels.fyi, a platform for tech workers to compare salaries, the median pay for prompt engineers is $150,000, reflecting the increasing importance of this skill in the AI-driven economy. For those looking to harness AI’s full potential, Askell’s advice is clear: be patient, be precise, and think like a philosopher.