Qwen 2.5
Base for LiveKit text turn detector
Episodes
-
#6237: Small Models, Big Questions: When Cheap Fables Get ExpensiveThree million fables for pennies — but can a small model tell a good example from a plausible one? -
#5524: Why AI Voice Agents Can't Hang UpTwo polite AI agents, one endless goodbye loop — and a phone bill that never stops climbing. -
#5520: Keeping a Fine-Tune Alive Across Model ReleasesDaniel wants to fine-tune DeepSeek Flash 4.1 on edited podcast scripts. The hard part isn't training — it's surviving the next release. -
#5467: Small Models, Big Schemas: When JSON Constraints BackfireSmall models plus strict JSON schemas should be a safe bet. A 15,000-generation study found the opposite. -
#5436: Small Models as Rewriters, Not WritersWhy "don't say X" prompts backfire, and how a tiny grammar-constrained model can scrub a script without breaking its grammar. -
#1073: Beyond YAML: Building the Agentic Smart HomeStop wrestling with YAML. Discover how MCP and local AI agents are transforming Home Assistant into a truly intelligent, aware partner.