AI-Smell Detector

Score forum and blog posts with an AI-generated probability to help readers trust what they read

Problem

A V2EX user complains that technical forum posts now have an unmistakable AI smell, so strong that they stopped reading entirely. This is a platform-level trust collapse, and readers need a tool to decide what deserves attention.

Solution

A browser extension and API that labels posts with an AI probability and expandable evidence, such as overused connectors, repetitive sentence templates, empty summaries, and lack of concrete failure details. User voting calibrates scores over time. Framed as reader aid, not author judgment.

Users

Heavy readers of tech forums, tech media editors, and teams screening submissions or outsourced work

MVP

A browser extension covering major tech forums and blogs; shows AI probability and three evidence points; one-click feedback on accuracy; no signup required, with optional local inference.

Revenue

Free extension for reach, then API billing per call for media, recruiting, and moderation; a team tier for bulk screening subscriptions.

Why now

AI-generated content has flooded technical communities and readers suffer more than authors; existing detectors have poor reputations, so a narrow, explainable focus on tech-post style can win.