It returns factually incorrect data, and it returns code with subtle but important errors if you ask it anything that's not regurgitated a thousand times in the training dataset.
Don't get me wrong, it has emergent properties (more than you would expect from a fancy autocomplete), but factual output was never GPT-4's nor any other LLM's design goal.
Don't get me wrong, it has emergent properties (more than you would expect from a fancy autocomplete), but factual output was never GPT-4's nor any other LLM's design goal.