Why intent prediction needs more than an LLM

Episode notes

Ryan sits down with Frank Portman, CTO at Yobi, to talk about why next-token prediction, though great for language, isn’t the right inductive bias for forecasting human behavior. They discuss how Yobi builds a “foundation model of behavior” using transformers and graph neural networks instead of chat-style LLMs, and what it takes to run millions of personalization decisions per second while keeping consumer data private. Episode notes: Yobi is a behavioral AI company building foundation models that predict future behavior for ad tech, marketing, and more.

• How do you turn AI coding chaos into a repeatable playbook?86 / 100
• Code isn’t the only thing causing your production failures
• Oh the places you’ll go with spatial data
• You don’t understand DNS like you think you do
• If context is king, architecture is the castle