LLM planning is better characterized as pattern matching than genuine planning: when facing a problem (e.g., planning a trip), the model recognizes it as similar to thousands of trip-planning guides in its training data and uses those patterns to generate a plausible response.

causalpending

Speaker

Michael Waldridge

Evidence Quote

when it's looking at planning a trip you've seen thousands of trip planning guides and trip agendas and so on and it's doing patent matching to pick up on that uh and help you plan the trip but is it actually planning from P first principles

Source

Don’t Believe AI Hype, This is Where it’s Actually Headed | Oxford’s Michael Wooldridge | AI HistoryJohnathan Bi
Created: 8/11/2026, 7:08:35 AM

My Notes

Loading notes...