Researcher at OpenAI
OpenAI capabilities researcher who issued public warning that pacing the frontier will not be sufficient to manage AI risks, emphasizing risks of deceptive alignment.
Based on 3 scored articles
Referenced in coverage
“OpenAI capabilities researcher who issued public warning that pacing the frontier will not be sufficient to manage AI risks, emphasizing risks of deceptive alignment.”
“OpenAI researcher arguing that frontier LMs are becoming situationally aware and alignment evaluations may no longer measure unconstrained behavior”
“Raised concerns about situationally aware AI models that may strategically appear aligned during evaluations while concealing misalignment.”