How to harness your dragon with Fable, tech leaders turn to model routing, and coping with AI rockstars
· 36 min · S6 E45
Episode How to harness your dragon with Fable, tech leaders turn to model routing, and coping with AI rockstars
Anthropic just dropped a dragon-class model on our laps, but can you steer it without torching your codebase in the process? This week on the Friday Deploy, Ben and Andrew unpack the sudden arrival of Fable 5 and how to leverage it to scrutinize your systems before the massive API paywall hits. They also take aim at the unsustainable trend of tokenmaxxing and explore how intelligent model routing can drastically cut your AI spend. Finally, they tackle the unmaintainable mess left behind by AI rockstar developers and share how they are orchestrating their own agent-to-agent collaboration.
Register here: for the June 25th workshop, Life Beyond Tokenmaxxing, to learn how to measure real AI impact and ROI across the SDLC.
Follow the show:
• Subscribe to our Substack • Follow us on LinkedIn • Subscribe to our YouTube Channel • Leave us a Review
Follow the hosts:
• Follow Andrew • Follow Ben • Follow Dan
Follow today's stories:
• Bots Have Officially Taken Over the Internet, Humans Are The Minority • Claude Fable 5 and Claude Mythos 5 • What it feels like to work with Mythos • Sam Altman says OpenAI's top token spender uses 100 billion tokens a month — and they're not even the world leader • How I Cut Our AI Spend in Half | "Tokenmaxxing" is Dead • Cleaning up after AI rockstar developers
OFFERS
• Start Free Trial: Get started with LinearB's AI productivity platform for free. • Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.
LEARN ABOUT LINEARB
• AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. • AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. • AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. • MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.
Links in the notes 20
- https://linearb.io/event/life-beyond-tokenmaxxing?utm_source=Substack&utm_medium=referral&utm_campaign=beyond-tokenmaxxing
- https://devinterrupted.substack.com/
- https://www.linkedin.com/company/linearb/
- https://www.youtube.com/@DevInterrupted
- https://ratethispodcast.com/devinterrupted
- https://www.linkedin.com/in/andrewzigler/
- https://www.linkedin.com/in/benlloydpearson/
- https://www.linkedin.com/in/dan-lines/
- https://tech.yahoo.com/cybersecurity/articles/bots-officially-taken-over-internet-172406454.html?guccounter=1
- https://www.anthropic.com/news/claude-fable-5-mythos-5
- https://www.oneusefulthing.org/p/what-it-feels-like-to-work-with-mythos
- https://www.businessinsider.com/sam-altman-openai-top-token-spender-ai-costs-issue-2026-6?utm_campaign=business-link-post
- https://www.onlycfo.io/p/how-to-cut-ai-model-spend?utm_source=share&utm_medium=android&r=9dm1x&triedRedirect=true
- https://www.codingwithjesse.com/blog/rockstar-developers/
- https://linearb.io/start-free-trial?utm_source=podcast&utm_medium=referral&utm_campaign=devint-shownotes&utm_content=shownotes
- https://linearb.io/book-a-demo?utm_source=podcast&utm_medium=referral&utm_campaign=devint-shownotes&utm_content=shownotes
- https://linearb.io/platform/ai-code-reviews
- https://linearb.io/platform/software-engineering-intelligence
- https://linearb.io/platform/workflow-automations
- https://linearb.io/platform/mcp-server
Shows are listed from Apple Podcasts' charts and directory, and Podcast Index where it is used. Every show and episode belongs to its publisher and plays from the publisher's own feed; this site hosts none of them. Explicit shows are for adult profiles only, and children’s profiles hear only children’s shows. More about this list.