AI Alignment Challenges
Seth and Jeremy discuss the challenges of aligning AI models, highlighting the vulnerability of machine learning models to out-of-distribution inputs. They explore the surprising effectiveness of certain models in handling adversarial attacks, shedding light on the complexities of aligning powerful AI systems.In this clip
From this podcast
Last Week in AI
#132 - FraudGPT, Apple GPT, unlimited jailbreaks, RT-2, Frontier Model Forum, PhotoGuard
Related Questions