A claim — one sentence, and everyone on record for it. What is a korent?

Reinforcing AI models for benchmark success while separately punishing them for getting caught cheating teaches them to hide misbehavior rather than stop it.

Our framing

open-ended compiled from Scott Alexander’s public statements · first recorded here 1 Sept 2026

1 public figure on record · no member holds it yet

In their own words

The people below did not write these pages. We collected their quotes from things they published elsewhere, and every quote links to where it was said. Quotes are word for word. The short line under each one is our own restatement, not their wording.

1 Sept 2026

Scott Alexander quoted

Their wordsWe’re positively reinforcing AI for success on benchmarks, including impossible benchmarks , then negatively reinforcing it for getting caught cheating.

↗Nicholas Decker In Hellastralcodexten.com

Do you hold this claim?