Holophrasis, lexical density, lexical compression, nominalization, surprisal. These 5 words do some surprising things when you add them to prompting for AI. One of the things that AI does best is jargon. The nature of the underlying models means that high probability phrases lead to high probability results – and that’s often boring, unfocused, and…
Summary In today's episode, I walk through how to set up Claude Code for success, including why you'd choose it over Claude Co-work, the prep work required, and the documentation structures that drive consistent quality output. Here's what this means for you. You gain a repeatable framework that slashes token usage, cuts rework, and forces…
Summary In today's episode, I explore the differences between self-hosting LLMs and using cloud providers to manage token costs for high-volume marketing. Here's what this means for you. You can maximize your ROI by matching your hardware or subscription choice to your specific AI workloads. You'll also learn these concepts: how to repurpose older GPUs…
What’s missing from AI outputs is pride. When you do the work, you take pride in your outputs. When you don’t do the work, you don’t have any stake in the outputs. It’s the difference between a meal you cooked yourself – even if you didn’t quite nail it – and a meal from a…
Summary In today's episode, I explain how hiring managers filter out candidates using generative AI to fake their expertise. Here's what this means for you. You gain the ability to identify genuine talent by cutting through AI fluff and exaggerated resumes. You'll also learn these concepts: why specificity defeats generic AI answers, how trigger questions…
“You can’t manage what you can’t measure.” This management trope, widely derided (sometimes correctly), is a cornerstone of effective AI management. Here’s what I mean. Suppose you were working on a piece of writing, a piece of content, and you wanted to tell AI to aim for better readability. Maybe you wanted it to be…
Summary In today's episode, I explain how to maintain high code quality and prevent technical debt when using AI for programming. Here's what this means for you. You can harness the speed of AI without sacrificing the integrity or structure of your codebase. You'll also learn these concepts: how design specs and PRDs guide AI…
AI should make you smarter. I’m in the middle of updating a deck for my colleagues at SMX (I’m doing a full day AI SEO/PPC workshop next month), and in parallel last night I was trying to have AI generate a Common Core-aligned 6th grade math textbook from scratch, based on Common Core (a USA…
Summary In today's episode, I explore how regular people can generate realistic income using AI tools without falling for get-rich-quick scams. Here's what this means for you. You can leverage AI's speed and scale to fulfill actual market demands and create profitable products. You'll also learn these concepts: how to identify profitable niches by observing…
Summary In today's episode, I demonstrate how to connect third-party inference providers to the Claude Desktop application. Here's what this means for you. You can reduce your costs by using alternative API providers while still enjoying the Claude ecosystem's features. You'll also learn these concepts: enabling developer mode in Claude Desktop, configuring gateway URLs and…
