Blog
Dan Klein on Why LLMs Are Plausibility Engines β and What It Actually Takes to Ship Reliable AI
Scaled Cognition co-founder and CTO Dan Klein joined the Chain of Thought podcast to explain why most AI prototypes die before they ship, why prompting is not a real control surface, and how APT-1 was architected from the ground up to give actions and information first-class status instead of treating everything as tokens