Episode 73 - Credit Where Credit Is Due

Come play AI or Not at the Esri UC (booth 436) and win a robot-head keychain!

Episode 72 - The Judge Pattern Goes to Washington

To bring Claude Fable 5 back online, Anthropic paired it with a smaller model that screens what you ask and what Fable answers. That's the "judge" pattern!

Episode 71 - Ask Better Questions

Educate yourself enough to "kinda get it," then ask good questions, then judge the output.

Episode 70 - AI or Not?

AI-generated and AI-altered images have gotten genuinely, unsettlingly good. That's wildly useful and also dangerous!

Episode 69 - Wait, what's the difference between a Skill and a Project?

A Skill is a repeatable task. A Project is reference material. Cowork is a Project that can use your computer. They aren't competing products; they are different places to put your context.

Episode 68 - Don’t Blame the Robot

Most “AI-driven layoffs” aren’t actually driven by AI. The technology is used as a cover for cuts that were already coming for different reasons. No one wants to admit the real reason, so it is easier to blame the robot.

Episode 67 - It’s not your prompts

Use AI for thinking (not deciding), fix the system (not the output), and correct without drama.

Episode 66 - Don’t Tell Claude Who to Be

Tell it what task it's doing and what scope it's working in. The "you are an expert" prompt is mostly cargo cult now; a list of NEVER statements is brittle.

Episode 65 - How to tend a codebase

I double down on the idea that keeping up with AI-generated code looks a lot like gardening: seeds, soil, water, pruning, weeding, and sometimes pulling up a plant.