# Perplexity — How AI Detectors Work and Why Scores Don’t Prove Authorship

- Company: Perplexity (perplexity.ai)
- Announced: 2026-09-15
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://www.perplexity.ai/hub/blog/ai-detector
- Record: https://forck.live/items/11130-how-ai-detectors-work-and-why-scores-don-t-prove-authorship
- Subject: Perplexity

Perplexity's guide explains how AI detectors work, covering classifiers, perplexity and burstiness, and why detection scores do not prove authorship. It notes that scores reflect the text and the evaluating system, and that different detectors can reach different conclusions about the same passage.

## Evidence

Verbatim from https://www.perplexity.ai/hub/blog/ai-detector:

> Perplexity and burstiness describe patterns in a passage. Those patterns may help explain why text was flagged, but they cannot establish who wrote it.

---

Record: https://forck.live/items/11130-how-ai-detectors-work-and-why-scores-don-t-prove-authorship
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md