"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

Exploitable by Default: Vulnerabilities in GPT-4 APIs and “Superhuman” Go AIs with Adam Gleave of Far.ai

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

CHAPTER

Exploiting Vulnerabilities in AI Go Players

This chapter investigates the inherent vulnerabilities of superhuman Go-playing AIs, particularly focusing on the case of Catego, which was outperformed by an adversarial AI using structured strategies. It highlights the broader implications for AI safety, demonstrating how even advanced models can be susceptible to targeted attacks, regardless of their sophistication. The discussion emphasizes the balance required between enhancing performance and ensuring robustness, exploring alternatives for safer AI design.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner