Learning to design for physical AI by exploring vision language models

“Meta’s Yann LeCun to launch physical AI startup after declaring LLMs a ‘dead end’” 👈 Want to learn to design for physical AI yourself?

You’ve probably seen the headlines: “The pioneering AI researcher is betting on a new paradigm that teaches machines to understand the physical world, not just language.”

Since the beginning of LLM hype in November 2022, it’s been clear that AI can’t stay in chat windows forever. To solve real problems, we need to bring AI into the physical world.

One way of doing that is with vision language models (VLMs). VLMs bring together LLMs with real-world scene understanding.

My collaborator Vitorio Miliano has been using VLMs to redact research recordings, building on our AI Doppelgangers project.

Now he’s teaching a live, online workshop on how to design with VLMs December 4 (that’s next week!).

If you want to get ahead of the curve and learn how to use the next big thing in AI, consider signing up.