My Weird Prompts

Why We Still Fine-Tune in 2026


Listen Later

In an era of massive context windows, why are companies still fine-tuning models? This episode explores the shift from teaching facts to shaping behavior. We discuss domain expertise, style alignment, and Text-to-SQL optimization, plus how Parameter-Efficient Fine-Tuning (PEFT) makes it accessible. Learn why fine-tuning creates specialized "neural highways" that outperform general models in production.
...more
View all episodesView all episodes
Download on the App Store

My Weird PromptsBy Daniel Rosehill