LLMs on the browser

Channel:
United States Google for Developers
Subscribers:
2,510,000
Published on ● Video Link: https://www.youtube.com/watch?v=43Xo2HBcR_o


Duration: 0:00
1,516 views
49

On-device large language models not only reduce latency and enhance privacy, you can also save money by not needing to run on a cloud server for interference.

Speaker: Jason Mayes
Products Mentioned: Web AI, Generative AI



Other Videos By Google for Developers


2024-08-21Machine Learning Crash Course: Logistic Regression
2024-08-20“You don't have to be perfect to make an impact!” + more advice from Google #DeveloperStudentClubs
2024-08-19Machine Learning Crash Course: Gradient Descent
2024-08-19Machine Learning Crash Course: Intro & What's New
2024-08-18Machine Learning Crash Course: The Optimistic ReLU Function
2024-08-15Can you spot what will create unexpected behavior in this code snippet?
2024-08-14Code like a minimalist—no need for complex tricks. Keep it clean, readable, and classy. ✨
2024-08-14What could possibly go wrong with a little code cleanup?
2024-08-13No need for two laptops, but thank you?
2024-08-13AI-assisted coding search results to help you Google it better
2024-08-12LLMs on the browser
2024-08-11Busting 3 myths about quantum computers
2024-08-08New in Web from Google - :has(), gradient.style and more
2024-08-08Determine the output of this C code using post-increment operators. Go!
2024-08-07Use scroll progress to start, pause, and reverse an animation on your web page
2024-08-07Save cats using Javascript, play Purrfect Code
2024-08-06The modern pentathlon.
2024-08-06Build with Gemini Nano on Android
2024-08-04The quest for a productive outdoor workspace continues...
2024-07-31When you leave your PM with more questions than answers. 🤷‍♂️
2024-07-30Google office ASMR