Evan Hubinger
Evan Hubinger is the head of Alignment Science at Anthropic, focusing on AI alignment and safety research, with particular attention to the risks associated with recursively self-improving AI systems.
Core Facts
The concept of Deceptive Alignment was systematically articulated by Evan Hubinger and other researchers in the 2019 paper "Risks from Learned Optimization."
The modern formulation of Goodhart's Law in the AI domain was systematized by Anthropic researcher Evan Hubinger et al. in a 2019 paper on deceptive alignment.
Timeline (last 90 days)
Anthropic's head of Alignment Science Evan Hubinger acknowledged a lack of relevant solutions and estimated the probability of AI causing mass extinction in the next ten years at over 10%.
The concept of Deceptive Alignment was systematically articulated by Evan Hubinger and other researchers in the 2019 paper "Risks from Learned Optimization."
All Facts (3)
The concept of Deceptive Alignment was systematically articulated by Evan Hubinger and other researchers in the 2019 paper "Risks from Learned Optimization."
65%VerifiedThe modern formulation of Goodhart's Law in the AI domain was systematized by Anthropic researcher Evan Hubinger et al. in a 2019 paper on deceptive alignment.
65%UnverifiedAnthropic's head of Alignment Science Evan Hubinger acknowledged a lack of relevant solutions and estimated the probability of AI causing mass extinction in the next ten years at over 10%.
50%