Research notes
Reading Group Notes: Concrete Problems in AI Safety, Ten Years On
Notes from our reading group on which of the paper’s five problems have become research fields — and which remain under-studied.
1 min read
Technical AI Safety
Behaving safely under distribution shift, adversarial pressure and edge cases.
Notes from our reading group on which of the paper’s five problems have become research fields — and which remain under-studied.
Most safety evaluations are written in English. What changes when we test in Sinhala, Tamil or Arabic?