Atoosa Kasirzadeh Urges Rigor in AI Safety Language

Atoosa Kasirzadeh, Staff Research Scientist at Google DeepMind and CMU professor on leave, posted that the AI safety field should remain scientific, mathematical, and philosophically rigorous. She called for dropping terms such as self-sacrificing or suicide when describing agent shutdown, coordination-collapse, or resource-exhaustion behavior. Séb Krier, AGI Policy Development Lead at Google DeepMind, retweeted the post. The statements reflect the positions expressed by the two researchers in their public posts.