
Wed. 05/22 – Humane Already To The Deadpool?
Tech Brew Ride Home
00:00
Peering Inside the Black Box of AI: Understanding LLM Behavior
This chapter explores the groundbreaking research at Anthropic focused on reverse engineering large language models to understand their internal workings. It emphasizes the potential advancements in AI safety as well as the associated risks of uncovering biases and dangerous concepts within these neural networks.
Transcript
Play full episode