Writing-scaffold MCP bypasses Pangram AI detector with 78–96% miss rates

amplifiedamp · x · 2026-11-16

Developer amplifiedamp released a writing-scaffold MCP prompt library plus a false-negative benchmark exploiting Pangram's weakness on text interspersed with non-AI features. The method, dubbed "structure transfer," uses the scaffold of a human writing sample to guide model writing.

Key results (pangram-4.1):

The author judged the method trivially reverse-engineerable and, encouraged by Pangram's maxspero, fully released the report, GitHub repo and a public endpoint, arguing community benefits outweigh harms. The prompt library is open-source and works with Pi, Claude Code and Codex.

Related event: Developer's prompt library benchmark fools Pangram AI text detector with up to 96% evasion(2 posts)→

Original post →

More from coding & agent

coding & agent channel →