Computers are learning to read our minds

Computers are learning to read our minds

The home team chats with Gašper Beguš, director of the Berkeley Speech and Computation Lab, about his research into how LLMs—and humans—learn to speak. Plus: how AI is restoring a stroke survivor’s ability to talk, concern over models that pass the Turing test, and what’s going on with whale brains.
Semantic search without the napalm grandma exploit (Ep. 600)

Semantic search without the napalm grandma exploit (Ep. 600)

Ben and senior software engineer Kyle Mitofsky are joined by two people who worked on the launch of Overflow AI: director of data science and data platform Michael Foree and senior software developer Alex Warren. They talk about how and why Stack Overflow launched semantic search, how to ensure a knowledge base is trustworthy, and why user prompts can make LLMs vulnerable to exploits.

The post Semantic search without the napalm grandma exploit (Ep. 600) appeared first on Stack Overflow Blog.