New Research Catches AI Cheating But The AI Shamelessly Hides The Evidence

In today’s column, I explore a newly released research study that intriguingly discovered that generative AI and large language models (LLMs) readily commit two bad deeds. First, AI cheats, which is presumably a bad thing to do (humankind doesn’t want that to happen). Second, the AI shamefully attempts to hide the evidence of the cheating. You could liken this to the circumstance that sometimes a committed crime is made…