@chetaslua put a live BS meter on the Trump versus Kamala debate with Jev: every sentence, both candidates, five yes/no questions each. They report 1,191 calls, 1.18M tokens, 415ms median, and $0.0497. Clips were picked by one fixed rule, and they say it is not a fact-check.

Chetaslua (@chetaslua) published this on 2026-09-17. @chetaslua put a live BS meter on the Trump versus Kamala debate with Jev: every sentence, both candidates, five yes/no questions each. They report 1,191 calls, 1.18M tokens, 415ms median, and $0.0497. Clips were picked by one fixed rule, and they say it is not a fact-check. 🚨 I gave the Trump vs Kamala debate a live BS meter using Jev every sentence, both candidates, 5 yes/no questions each 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 same questions for both, clips picked by one fixed rule, not a fact-check https://t.co/m8u4ALl6Me How Jev or TypeSafe is used, in the post's own words: “🚨 I gave the Trump vs Kamala debate a live BS meter using Jev every sentence, both candidates, 5 yes/no questions each 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 same questions for both, clips picked by one fixed rule, not a fact-check https://t.co/m8u4ALl6Me” The post does not name a separate audience. It is for people reading what @chetaslua shows here (it quotes @CompleteSkeptic; it includes media).