1010: Fable 5 as Advisor: Anthropic's Two-Model Pattern for Smarter, Cheaper Agents
About this episode
Jon Krohn discusses Anthropic's advisor strategy for AI agents, highlighting its efficiency and cost benefits.
In Episode #1010, Jon Krohn digs into “the advisor strategy”, a clever pattern that pairs a fast, cheap executor model with a frontier-class advisor it can consult mid-task, all inside a single API call. Every agent builder faces the same tension: frontier models plan best but cost too much to run on every turn, while small models fumble the decisions that matter. Anthropic’s advisor tool resolves it with roughly a one-line code change, and the benchmarks are startling: Sonnet with an Opus advisor scored higher than Sonnet alone while costing 11.9% less, and Haiku’s BrowseComp score more than doubled at 85% lower cost than Sonnet solo. Jon covers the newest Fable 5 numbers, the practical gotchas, how it differs from OpenAI’s router and why AI progress is now as much about composing models as training bigger ones. Additional materials: www.superdatascience.com/1010 Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
People in this episode
Host: Jon Krohn
Mentioned in this episode
Organizations: Anthropic
Products: Fable 5, Sonnet, Opus, Haiku, BrowseComp, OpenAI
More episodes of Super Data Science: ML & AI Podcast with Jon Krohn
- 1011: The Math Still Matters: Deep Skills in the Age of AI, with Dr. Catherine Williams
- 1009: How AI Is Quietly Saving Lives, with Steve Mock
- 1008: The AI-Native Startup Playbook
- 1007: How to Find Solid Career Ground in the AI Era, with 80,000 Hours Founder Ben Todd
- 1006: In Case You Missed It in June 2026
- 1005: People Skills for Analytical Thinkers, with Bestselling Author Gilbert Eijkelenboom
Explore listener stats, chart rankings, contacts and more on the Super Data Science: ML & AI Podcast with Jon Krohn podcast page.