Atoosa Kasirzadeh Urges Rigor in AI Safety Language
Atoosa Kasirzadeh argued that AI safety work needs scientific and mathematical precision instead of loaded terms.
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.
One of the most useful contribution the AI safety field can make right now is to stay *scientific and mathematical and philosophically rigorous*. This means dropping loaded language like “self-sacrificing” or “suicide” when describing agent shutdown, coordination-collapse, or…
Combined views
39
2 posts, first seen 6d ago
Atoosa Kasirzadeh Urges Rigor in AI Safety Language
Atoosa Kasirzadeh argued that AI safety work needs scientific and mathematical precision instead of loaded terms.
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.
One of the most useful contribution the AI safety field can make right now is to stay *scientific and mathematical and philosophically rigorous*. This means dropping loaded language like “self-sacrificing” or “suicide” when describing agent shutdown, coordination-collapse, or…