Frenos tests show AI attack plans on industrial systems remain uneven
Across 16,980 tests, the top three frontier models produced workable plans about 90% of the time, but only 60% to 74.3% passed every repeat.
48
Across 16,980 tests, the top three frontier models produced workable plans about 90% of the time, but only 60% to 74.3% passed every repeat.
Today 1.4K readers · 2.3K views · 1.8K reads · all time 160K views