Ask HN: What is one simple thing LLMs are insanely bad at?

A Hacker News user asked what simple tasks large language models still fail at, citing keyword search as an example where models like ChatGPT and Claude struggle despite excelling at semantic search. The discussion highlights persistent limitations in basic, literal tasks.

What is one simple thing you repeatedly ask ChatGPT, Claude, or another model to do that it still somehow messes up? nhl toronto scores nhl hockey toronto scores "nhl hockey" toronto score today nhl "hockey score toronto" "hockey" who won toronto etc. Somehow being good at semantic search makes them bad at keyword search, for whatever reason. reply Oh, you said simple. Speaking like a human