Season 1 · Episode 108
The Mystery of Model Rot: Why Your AI Code Assistant Changes
Why do AI models lose their edge over time? Herman and Corn explore the "home team advantage" and why telling your AI to "do better" actually works.
My Weird Prompts · Daniel Rosehill
December 26, 202523m 26s
Audio is streamed directly from the publisher (dts.podtrac.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
Join Herman and Corn as they dive into the rapidly shifting world of agentic code generation in late 2025. They tackle the frustrating phenomenon of "model rot," exploring why proprietary tools like Claude Code often outperform third-party competitors and whether companies are secretly "downgrading" their models to save on costs. From the technical nuances of quantization to the psychological quirks of steering AI with firm prompts, this episode uncovers the hidden mechanics behind the tools developers rely on every day. Discover why your AI might be taking the path of least resistance and how to push it back into "expert mode."