How to be convincing when talking to people about existential threat from AI
"AI alignment" 相关文章
Things I've Become More Confident About
Reason About Intelligence, Not AI
Anthropic's Pilot Sabotage Risk Report
What can we learn from parent-child-alignment for AI?
Why Would we get Inner Misalignment by Default?
A Very Simple Model of AI Dealmaking
No title
AIs should also refuse to work on capabilities research
A New AI Research from Anthropic and Thinking Machines Lab Stress Tests Model Specs and Reveal Character Differences among Language Models
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
Worlds Where Iterative Design Succeeds?
Reminder: Morality is unsolved
Reminder: Morality is unsolved
Differences in Alignment Behaviour between Single-Agent and Multi-Agent AI Systems
Differences in Alignment Behaviour between Single-Agent and Multi-Agent AI Systems
Should AI Developers Remove Discussion of AI Misalignment from AI Training Data?
Why AI alignment matters today
Why AI alignment matters today
