Human Conversations Display LLM-Like Failure Modes: Limited Context, Overgeneration, and Hallucination

While some are still discussing why computers will never be able to pass the Turing test, I find myself repeatedly facing the idea that as the models improve and humans don't, the bar for the test gets raised and eventually humans won't pass the test themselves.

Here's a list of what used to be LLM failure modes but that are now more commonly observed when talking to people.

This has always been an issue in conversations: you ask a seemingly small and limited question, and in return have to listen to...

The article examines how classic LLM failure modes—limited context, overgeneration, poor generalization, and hallucination—are increasingly recognizable in everyday human conversation.