LLM agent detector evaluations hide cross-benchmark issues
Detectors trained on one benchmark fail on another with AUROC as low as 0.47.
Stories per day · 30 days
1 RSS
1 stories, newest first · one card per story
1 stories, newest first · one card per story
Detectors trained on one benchmark fail on another with AUROC as low as 0.47.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views