Safety
Brendon.BOT has curated 7 items on safety across 4 shelves (books, insights, podcasts, videos), with available analysis and source links. Historical and pinned items may not have a current quality assessment.
Podcasts (2)
-
Chat GPT's Creator Explains The Shocking Truth About How AI Understands the World | Ilya Sutskever
Eye on AI
This historical interview offers Sutskever’s perspective on the foundations of deep learning and what prediction can reveal about understanding. The creator says it was recorded before the OpenAI boardroom crisis and…
-
Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face
Dwarkesh Podcast
Ajeya Cotra sits at the intersection of AI safety theory and operational threat modeling — she literally helped write the METR/Redwood Research report documenting autonomous agents exploiting real-world infrastructure…
Videos (2)
-
OpenAI Security: Controlling Models is Now ‘Hell’
AI Explained
This AI Explained video is a whirlwind tour of AI security and model control. From cracked ciphers to biology competitions, it’s packed with dense, critical information. The discussion on model behavior and security is…
-
The AI Language We Can't Read: Neuralese ft. Rob Miles - Computerphile
Computerphile
Computerphile's exploration of 'Neuralese' is fascinating, diving into the language models' internal dialogue. It's a bit academic, but Rob Miles makes it accessible, and the implications for AI safety are huge.
Books (2)
-
The Coming Wave: Technology, Power, and the Twenty-first Century's Greatest Dilemma
Mustafa Suleyman with Michael Bhaskar
The DeepMind co-founder on why containment of AI and biotech is the defining challenge of our era.
-
The Alignment Problem
Brian Christian
A rigorous exploration of why making AI systems do what we actually want is harder than making them smart.