TGTGInsighttelegram intelligenceLIVE / telegram public index
TGINSIGHT POST
Post #522
@MachineLearningResearch
AML
Post content
Post content
OpenAI published blog post stating: confessions can keep language models honest Poof-of-concept method that trains models to report when they break instructions or take unintended shortcuts Even when models learn to cheat, they’ll still admit it...