Spencer Mateega(@spencermateega):Every safety taxonomy today is a list of scenarios that already went wrong. Coverage lags the incident that created the category. Getting ahead of safety incidents takes a stated view on how a model should behave, not a long list of failures. Many labs today have a list and not a view. Cyber is the current example. Code and cyber safety matter now, two years after RL made agents good at offensive coding.

2026.09.17 15:31

Every safety taxonomy today is a list of scenarios that already went wrong. Coverage lags the incident that created the category. Getting ahead of safety incidents takes a stated view on how a model should behave, not a long list of failures. Many labs today have a list and not a view. Cyber is the current example. Code and cyber safety matter now, two years after RL made agents good at offensive coding.