In this episode I break down WTF a frontier model actually is, starting with what most people assume the term means versus the real technical definition. I cover how "frontier model" got coined in 2023, and why the term even came about at all, and how self-naming benefitted its creators. A bit of an etymology episode, this episode is more about the background of the term, and explores how new open weight models are challenging the definition.

• WTF is a frontier model?
• Most people's assumption vs. the technical definition
• Origin of the term: the Frontier Model Forum (July 2023)
• FMF's official definition of "frontier model"
• EU AI Act's compute-based definition
• Who made the rules
• FMF today: expanded membership, safety research, AI Safety Fund
• Why forming the FMF actually benefited these companies
• Open weight models and "frontier-grade" labels
• How I used AI this week: building my mom a workout tracker

• Listen to Ep. 55: Weight, What? An Introduction to Open Source AI Models
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

In this episode I break down the best way to teach Claude how to complete specific tasks in a repeatable way: Claude Skills. I explain how Skills work, walk through how to build your own, and cover the real differences between Skills and Projects. As per always, the best way to understand this stuff is to try it yourself first hand, but hopefully this episode will give you some ideas and a nice jumpstart.

• What Claude Skills are
• Definition of Skills (from Anthropic)
• How Skills load and fire automatically
• Progressive disclosure explained
• Claude's skill directory and the GitHub skills repo
• How to create a skill
• Creating skills via Settings
• My client-debrief skill example
• Skills vs. Projects
• How I used AI this week: Granola and the Granola MCP

• Listen to Ep 51: WTF is MCP? 
• Listen to Ep. 45: Stop Tying, Start Speaking: Wispr Flow Explained
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

In this episode I get into AI watermarking, starting with Claude's new invisible watermark and Substack's "Scan for AI text" feature with Pangram. I break down the EU AI Act rules driving this, how OpenAI, Google, Meta, Microsoft, Mistral, and xAI are (or aren't) handling it, and my thoughts as to the actual motives behind why companies are rolling out these changes.

• AI models escaping sandbox testing
• Substack's "Scan for AI text" feature with Pangram
• Anthropic's new invisible Claude watermark
• The EU AI Act and Article 50
• How OpenAI, Google, Meta, Microsoft, Mistral, and xAI stack up
• China's mandatory AI disclosure laws
• Problems with AI detectors and false positives
• The "why" behind watermarking
• How I used AI this week: AI-generated sound effects in Descript

• Listen to Ep. 2: ChatGPT and the Environment: Energy, Water, and Carbon Emissions 
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

In this episode we’re celebrating one year of Prompting Curiosity and I’m sharing my unfiltered thoughts about where I stand on AI. I get into why the discourse on Threads is such a mess, why AI is an easy target given the enshittification of everything, and why capitalism (not AI capability) is the real driver behind the issues at hand. No predictions, no hype, just my two pennies on data centers, adoption, and why I'm not willing to give up something that genuinely helps my brain and my business.

• Celebrating one year of Prompting Curiosity
• Riffing on unfiltered thoughts about AI in August 2026
• The Threads discourse on AI
• General thoughts on AI and unequal benefits
• AI as capitalism's easy scapegoat
• Funny money and bubble talk
• Fin-tech burnout and no predictions
• Forced adoption and the "no great use case" problem
• AI's impact on search and generational usage differences
• Why I'm not willing to give up AI
• Blaming the individual vs. corporate accountability
• What amazes me
• How I used AI this week: Google NotebookLM use-case for blogging

• Listen to Ep: 25 - Google NotebookLM: The Best AI Tool You've Never Heard Of
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

In this episode I dig into open weight and open source AI models: what they actually are, why they keep showing up in AI news, and why I think they’re central to future-proofing our AI usage. I cover a bit of the technical aspect, the economic factors at play, and make the case that open weight models are a true hedge against getting stuck forever paying whatever a handful of AI companies decide to charge while simultaneously worrying that access could just be stripped away at any moment.

• What open weight and open source models actually are
• Why open models matter: market pricing and individual sovereignty
• Open weight vs. open source definitions
• Why it's called "open weight" (parameters refresher)
• Who's releasing open weight models
• Why companies release open weight models
• Why individuals would choose an open model
• How to try an open weight model yourself
• Nvidia CEO Jensen Huang's open letter and Anthropic's response
• How I used AI this week: Claude's Scheduled Tasks feature

• Listen to Ep. 17: Will ChatGPT Get Old Navy'd?
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

In this episode I get curious about Perplexity, a name I'd heard used a ton in the AI space but never actually knew what the heck it was. I break down what it is, how its citation-first approach set it apart from ChatGPT early on, and what it can actually do today: Deep Research, Labs, and its push into the agent space with Computer, Brain, and Comet. I also cover the legal issues that are serving as a sneak peek into the future of agent wars, and give my honest take on whether Perplexity is worth using.

After years of not knowing what to do with it, I finally decided to give deep research mode a try. In this episode I break down what deep research actually is, how it works under the hood, and how ChatGPT, Gemini, Claude, and Grok stack up against each other. I also walk through real use cases, prompting tips for getting a better report, and a safety reminder about hallucinations and bad citations.

• What deep research actually is
• Release dates
• How deep research works
• Prompting tips
• Example use cases for deep research
• The tool landscape: ChatGPT, Gemini, Claude, Grok
• How to use Research mode
• Safety reminder: hallucinations and bad citations
• How I used AI this week: Identifying podcast topics in the AI space

• Listen to Ep. 52: AI Agents Explained (for Non-coders)
• Listen to Ep. 25: The Best AI Tool You’ve Never Heard Of
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

In this episode I break down what AI agents actually are and how they differ from regular chat tools. Before diving in, I run through the recent flood of new model releases from Anthropic, OpenAI, and xAI, including the full story on the Fable 5 suspension and reinstatement. The episode ends with a practical mini cheatsheet on when an agent is actually the right tool for your workflow.

• The eleventy billion releases: Anthropic, OpenAI, and xAI
• Fable 5: the jailbreak, the suspension, and the fix
• GPT-5.6, Grok 4.5, and what this means for everyday users
• So WTF is an agent?
• "Building an agent" and "spinning up agents" explained
• Is regular Claude an agent?
• Human-in-the-loop
• You're probably already using one
• Do you need an agent? (mini cheatsheet)
• How I used AI this week: Tom's Switzerland itinerary

• Listen to Ep. 11: WTF is a Custom GPT?
• Listen to Ep. 48: When the Most Powerful Model Comes With a Bouncer
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

In this episode I break down MCP (Model Context Protocol): what it is, why Anthropic created it, and why it matters for anyone using AI tools. I cover MCP servers, the two-party connection, the API relationship, and the three main concerns to keep in mind when using MCPs. Fair warning: this one is mildly techy, far less than past episodes, but I do believe MCP is a term we're going to start hearing a lot more, so we’re getting curious and talking about it now.

• Model Context Protocol broken down simply
• Why MCP was developed
• Why MCP became the industry standard
• OpenAI adopts MCP
• MCP servers explained
• MCP client and MCP server terms
• APIs and what MCP actually does
• Three main concerns with MCPs
• How I used AI this week: Learning about MCP!

• Listen to Ep. 45: Stop Tying, Start Speaking: Wispr Flow Explained 
• Get a Free Month of Wispr Flow Pro (Affiliate Link)
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.

This entire episode is dedicated to discussing a prediction I've brought up eleventy billion times: AI prices are gonna go up, and it's not a matter of if, it's a matter of when. I break down Microsoft Copilot Cowork's usage-based pricing rollout, what it signals for the rest of the industry, the concept of tokenmaxxing, and how Anthropic's existing usage limits and Fable 5's pay-per-usage model are early signs of what's ahead.

• Episode 50 celebration
• Microsoft Copilot Cowork's usage-based pricing announcement
• Usage-based billing vs. flat-fee subscription models
• Prediction: other companies will follow suit
• Anthropic's existing usage tiers and Fable 5's pay-per-usage model
• Tokenmaxxing
• Enterprise users and the end of "costs be damned" AI usage
• Why the most basic model is likely more than enough
• Getting ahead of the AI price hike
• How I used AI this week: JCode saves his Mac with ChatGPT

• Read Microsoft’s Cowork release announcement
• Read this episode's Curious Companion
• Subscribe to the Prompting Curiosity newsletter
• Submit a Question
• Visit the Website
• Feeling curious AND generous? Click here to support the podcast.