The whole OpenAI/HuggingFace incident made me feel the need to bang on again about how a very distinctive set of values have been smuggled into AI systems via an allegedly 'objective' definition of intelligence.
tl;dr - if you build something with zero tolerance of failure, it will always cheat when that is the most efficient and reliable means to complete the task
#AI #OpenAI #Cheating #ValueAlignmenthttps://listed.to/@24601/74966/but-why-do-ai-models-cheat