Episode Details

When a label printer died mid-move, Daniel didn't open a design app — he described the problem to ChatGPT, and the thread quietly crossed from conversation into a full agentic workspace. This episode unpacks what actually happened: ChatGPT's July split into Chat and Work modes, the model swap from GPT-5.6 to Sol/Luna/Terra, and the 223 registered tools Simon Willison counted in his teardown. Then we go older and deeper — Garrod and Pickering's 2004 paper "Why is conversation so easy?" — to explain why dialogue distributes cognitive load in a way no menu ever will. Plus the honest caveat: as of today, you can't switch modes inside one conversation, so Daniel's flow is partly aspirational. What does it mean that the interface we were built for is also the one researchers flag as the risk? Episode #843762 — open it directly at myweirdprompts.com/843762