A Classical Operating Manual for Spotting Bad-Faith Arguments in Public Forums
Promptmethus · x · 2026-09-27
The author shares a standalone diagnostic prompt system, built on Greek and Roman rhetorical distinctions, that AI models can apply to analyze arguments on X, podcasts, and comment threads.
- Two contests: Dialectic is joint truth-seeking under agreed rules (binding only when parties actually entered it); Eristic is victory-seeking by any means—shifting the contest's ground is a primary eristic weapon. Public spaces like the Athenian agora defaulted to eristic, where ethos, pathos, and ridicule were ordinary tools.
- The binding-condition test: Did parties explicitly agree to formal academic rules? Is this a closed seminar or an open thread? If the latter, unilaterally demanding stricti iuris procedure (hyper-literal definitions, etiquette policing) to claim victory is itself bad faith.
- Rule 1: Treating school etiquette as binding law when no disputatio was agreed upon is a bad-faith move in itself.
The manual includes definitions, tests, and an output format so other models can apply it without prior files.
More from coding & agent
- User finds a long-running Amp orb quietly burning his Codex usage — bytebot · 2026-09-27
- Block open-sources Buzz: a self-hostable Slack-like workspace where humans and AI agents share rooms — bibryam · 2026-09-27
- Microsoft open-sources Scope, an agentic experience evaluation platform (research preview) — lee_stott · 2026-09-27
- Hermes Agent ships major updates: bot mode, local AI, improved subagents and HUD — lifebypixels · 2026-09-27
- A Cheap AI Prompt Can Still Create an Expensive Business Process: Measure Full Task Cost, Not Token Price — rvp · 2026-09-27
- One flipped memory wipes out all agent memory gains; only external confirmation stops it — Danculus · 2026-09-27