{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/69ab3b7c7036d739021982df/6a0ddc28d7997e788cf87250?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"MIT Says Half Your AI Gains Come From How You Ask. Not the Model.","description":"<p>Now I have the full transcript. Building the deliverable.</p><p><br></p><p>What's really happening inside prompting now that AI agents are 100x more powerful than six months ago? The common story is that prompt engineering is dead — but the reality is more complicated.</p><p><br></p><p>In this podcast, I share the inside scoop on the AI Question Method and why heavy knowledge work with frontier models demands a new mental model:</p><p>• Why prompt engineering is now table stakes, not a skill </p><p>• How to treat AI like a senior partner, not a junior </p><p>• What three question principles unlock agentic knowledge work </p><p>• Where most users still prompt like it is 2025</p><p><br></p><p>For operators and builders, the agentic shift is a real opportunity, but only if you evolve your prompting alongside the models and learn to ask sharper questions instead of issuing tasks.</p><p><br></p><p><br></p><p>Subscribe for daily AI strategy and news. For deeper playbooks and analysis: https://natesnewsletter.substack.com/</p><p><br></p>","author_name":"Nate B. Jones"}