{"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/6affaef118a3c93bdb825615?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"Your AI can write a thousand questions when you needed the 50 best answers. How to keep a long run pointed at what you want now, even as the goal shifts","description":"<p>The full post, with prompts and worksheets for running longer AI work on your own and with a team: <a href=\"https://natesnewsletter.substack.com/p/long-running-ai-agents?utm_source=podcast&amp;utm_medium=podcast&amp;utm_campaign=long-running-ai-agents-launch&amp;utm_content=show-notes\" rel=\"noopener noreferrer\" target=\"_blank\">https://natesnewsletter.substack.com/p/long-running-ai-agents?utm_source=podcast&amp;utm_medium=podcast&amp;utm_campaign=long-running-ai-agents-launch&amp;utm_content=show-notes</a></p><p><br></p><p>What&#39;s really happening when an AI agent works all night?</p><p>OpenAI and Anthropic report AI agents working for hundreds of hours and for days. The common story is that longer runs just need a smarter model, but the real question is whether your agent has the current decisions, examples, and instructions behind the work.</p><p><br></p><p>In this episode, I share the inside scoop on long-running AI agents:</p><ul><li>Why my research run produced a thousand questions I didn&#39;t need</li><li>How treating project information like code keeps agents on current decisions</li><li>What shared skills and permissions change when many agents touch the same work</li><li>Where to start alone with one job you keep explaining</li></ul><p>An overnight run can save you a day or cost you one, and the difference is the structure you give it.</p><p><br></p><p>Subscribe for daily AI strategy and news.</p><p>Hosted on Acast. See acast.com/privacy for more information.</p>","author_name":"Nate B. Jones"}