
#15: Digging into explainable AI
Unaligned with Robert Scoble
00:00
Harnessing Speed in AI Through Compact Models
This chapter explores speed improvements in large language models (LLMs) and their impact on user interactions with digital assistants. It discusses the feasibility of running advanced models on low-power devices, paving the way for faster and more accessible AI applications.
Transcript
Play full episode