How I AI: Which AI model should I use for which task?

How I AI: Which AI model should I use for which task?

June 28, 2026 · 17 min

About this episode

The episode discusses how to choose the right AI model for specific tasks and the implications of token usage in AI applications.

If you've ever stared at a model picker and wondered whether to click Flash, Sonnet, Opus, Instant, or Think Deeper, you are not alone. These naming conventions are genuinely confusing, and most people just pick something and hope it works. The stakes are higher than they might seem, though. Token misuse has left some companies with eye-watering AI bills, including one case where a single employee ran up a $500,000 tab in a month.  The good news is that there is a simple mental model that cuts through all the noise, and once you have it, choosing the right model for any task takes seconds.  In this How I AI episode, Neo and I walk through the four major AI platforms, Gemini, ChatGPT, Claude, and Copilot, and break down exactly which model to use and when. We also get into tokens, usage limits, and why matching the model to the task matters far more than most people realise.  How I AI is a special series within How I Work where Neo and I explore how high performers are using AI at work to boost productivity, make better decisions and reduce overwhelm.  What you'll learn:  Why ignoring model numbers and reading the small…

People in this episode

Host: Amantha Imber

Guest: Neo

Topics covered

Keywords

Mentioned in this episode

Organizations: Fable, Mythos

Products: Gemini, ChatGPT, Claude, Copilot, Flash, Sonnet, Opus, Instant, Think Deeper

More episodes of How I Work

Explore listener stats, chart rankings, contacts and more on the How I Work podcast page.