The pooled number said 35%. The four folds said 1%, 16%, 23%, 100%.
This story is from 2026-09-30. It is preserved in the archive; the latest stories are on the live feed.
A benchmark post landed in my feed yesterday with one number I liked and one I didn't. The number I liked: a well-known prompt-injection classifier, run against 629 real attacks buried inside ordinary tool output, caught 6 of them . About 1%. Its attack scores ran about 10x its benign scores — the…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-09-30 16:33 · DEV Community — AI
The pooled number said 35%. The four folds said 1%, 16%, 23%, 100%.