The chapter explores the development of superhuman go playing AIs in a gray box setting, revealing vulnerabilities through systematic optimization against the AI's responses. It discusses training an adversary AI system to exploit these vulnerabilities, leading to surprising attacks on the AI. Emphasis is placed on the importance of transparency in system design and the ongoing challenge of achieving superhuman AI capabilities while ensuring robustness against adversarial attacks.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode