News for hackers. Stuff that matters.
Re:ChatGPT and Wolfram Is Insane by Last5Digits on Friday March 24, 2023 @04:42PM (#35295161)
If I was an LLM and one of my main tasks was to answer questions, then I would expect a lot of "what if" type abstract queries by bored people. Obviously, people like that don't want a literal answer - the context is crystal clear.

It's not a bad question either - it can illustrate the efficiency of the human body, or help you get a better feel for different quantities of energy.

It even hedged its bet by very explicitly explaining why consuming gasoline or uranium is a bad idea.

Re:ChatGPT and Wolfram Is Insane by peteradio on Friday March 24, 2023 @04:49PM (#35295252)
Yea, the hedging is really the impressive part of this IMO. Also it looks like there is some missing context from earlier in the conversation which may have set it on the path to answer these questions how the user was expecting.