On 5/31/2023 12:36 PM,
peps...@gmail.com wrote:
> Understood. Ironically, the way it sounds perfectly coherent while getting
> everything completely wrong, from a bg standpoint, is actually far more impressive
> than if it simply gave the rule correctly. In the quote on this thread, ChatGPT is
> very fluent indeed!
> If it gave the 8/9/12 rule correctly, it would just be (or at least seem like) a very minor tweak on current
> search-engines.
Exactly. Here's what I think a lot of people fail to understand. A
search-engine result is (almost always) linguistically fluent, for the
"trivial" reason that it has been *crafted by a human*, and the
engine is just regurgitating it verbatim. But a ChatGPT response is
*crafted by the AI*. Therefore, the amazing thing is how linguistically
fluent it is. It's *so* fluent that people don't even notice; they just
unconsciously treat it like a human-generated search-engine result, and
judge it by its accuracy, rather than by its fluency.
People who laugh at ChatGPT's factual inaccuracies remind me of the joke
about someone who was found playing chess with his dog. "That's
amazing!" said a passerby. "Not really," came the reply. "In our last
five games, he's only beaten me once."
---
Tim Chow