AI detector Pangram's known failure modes, including private diary entries

JeremyNguyenPhD · x · 2026-09-04

Byrne Hobart notes Pangram, though well-regarded among AI detectors, has known failure modes: secondhand anecdotes of it not working, old school essays flagged as AI with no proof available, and misjudgments shaped by other detectors' errors. Jeremy Nguyen amplifies with another limitation: personal diary entries that can't be shared or redacted in detail are also hard to adjudicate — a caution for anyone relying on AI detectors.

Original post →

More from Safety

Safety channel →