
Dr. Maor Farid, Co-Founder & CEO at Leo AI
Yann LeCun says LLMs will never reach human-level understanding with text alone. Discover why geometry breaks GPT — and how Leo AI’s Large Mechanical Model (LMM) empowers mechanical engineers to search CAD parts and generate assemblies.
Yann LeCun, one of the godfathers of modern AI, recently said:
“Large language models will never get to human level by just training on text. We’ve got to train models to understand the real world.”
For mechanical engineers, this statement feels like common sense.
It doesn’t matter how massive GPT becomes,
how many billions of dollars are invested in OpenAI,
or how much data it consumes from the internet —
it will never match the skills of a first-year mechanical engineering student at a community college when it comes to something as basic as matching a bolt to a hole.
Why LLMs Can’t Think Like Engineers
The reason is simple: GPT is a language model. And language can’t describe geometry.
Ask any engineer to explain a mechanical concept, and within a minute, they’ll grab a marker and sketch it on a whiteboard (badly, usually). We think in shapes, constraints, and spatial relationships — not just words.
From Words to Parts: Introducing the Large Mechanical Model (LMM)
That’s why at Leo AI, we built the first Large Mechanical Model (LMM).
Unlike LLMs that use words as tokens, the LMM uses mechanical parts as tokens. It’s designed to understand CAD — not just read descriptions of CAD.
This allows engineers to:
Search CAD parts across internal PLM systems and online catalogs using free language.
Understand geometric constraints and relationships between parts.
Soon: Generate assemblies and complete product designs directly from a description.
Why We Built It
We’re not building a new foundational model because we want to look cool.
We don’t care about writing patents for the sake of press coverage or publishing papers to collect citations.
We built it because we had no choice.
For engineers to search and design effectively with AI, the model must think in geometry — something LLMs will never do.
Why can’t GPT match even a freshman mechanical engineer?
What did Yann LeCun say about language models and their limitations?
What is the Large Mechanical Model (LMM)?
What capabilities does the LMM enable for engineers?
Why did Leo AI build the LMM?
What does Leo AI’s LMM bring to mechanical engineers?
Ready to try Leo? Try Leo Today
Enjoyed this article on Why GPT Will Never Match a Freshman Mechanical Engineer - Leo - Generative AI for Engineering CAD Design? Don’t miss How GenAI Will Revolutionize Product Design - Leo - Generative AI for Engineering CAD Design





