# Why intent prediction needs more than an LLM

DevFeed: [Why intent prediction needs more than an LLM](<https://devfeed.tech/articles/why-intent-prediction-needs-more-than-an-llm-2184.md>)

Original publisher: [Read original article](<https://stackoverflow.blog/2026/06/30/why-intent-prediction-needs-more-than-an-llm/>)

Author: Phoebe Sajor

Published: 2026-06-30T07:40:00Z

Content type: article

Language: en

Sources: [Stack Overflow Blog](<https://devfeed.tech/sources/stack-overflow-blog.md>)

Topics: [foundation-models](<https://devfeed.tech/topics/foundation-models.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [data](<https://devfeed.tech/topics/data.md>), [Deep neural networks](<https://devfeed.tech/topics/deep-neural-networks.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [data](<https://devfeed.tech/tags/data.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [math](<https://devfeed.tech/tags/math.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [se-stackoverflow](<https://devfeed.tech/tags/se-stackoverflow.md>), [se-tech](<https://devfeed.tech/tags/se-tech.md>), [transformers](<https://devfeed.tech/tags/transformers.md>)

## AI overview

Ryan Donovan interviews Frank Portman, CTO at Yobi, about why large language models are not the right inductive bias for predicting human intent and behavior. The discussion covers Yobi's behavioral foundation models, which use transformers and graph neural networks to support large-scale personalization while keeping consumer data private.

## Source excerpt

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.