12 citations · 21 across the 9 of their papers we have counts for
Showing 2026 · cs.CYShow all
2 papers · 2 filters
cs.CY2026
Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions
Stephen Barrett, Robin Bloomfield, Alexandra Chirilă +3
Decision makers need sufficient understanding to make good decisions about training or deploying frontier AI systems. However, such decisions are increasingly made under time-press…
cs.CY2026
Lessons from External Review of DeepMind's Scheming Inability Safety Case
Stephen Barrett, Francisco Javier Campos Zabala, Sean P. Fillingham +4
Safety cases for frontier AI systems should provide a convincing argument, supported by evidence, that the risk of harm is within an acceptable bound. When developers author their…