News for hackers. Stuff that matters.

A comment on Building a ChatGPT Enhanced REPL. Parent comment

Re:Building a ChatGPT Enhanced REPL by og_kalu on Friday April 21, 2023 @12:52AM (#35649927)
The point is that a distinction without a difference is a meaningless distinction. Shouting "This is not real [insert property]" is beyond meaningless. Either this supposed difference is important enough to manifest in reality/output or it functionally doesn't exist.

If rationalizations work as well as human ones do then treat them as you would human ones.

[ Parent | on HN ]
Re:Building a ChatGPT Enhanced REPL by wpietri on Friday April 21, 2023 @12:55PM (#35656613)
Yes, ergo I believe there are differences.

But you didn't address my point. Do you believe that explanations produced via tarot or zodiac should be treated with that same level of deference? That explanations from ouija boards are things we "might as well go with"?

[ Parent | on HN ]
Re:Building a ChatGPT Enhanced REPL by og_kalu on Friday April 21, 2023 @04:28PM (#35659614)
GPT-4 doesn't not perform at the same level on tasks as a ouija board. The whole point is that the level of deference is based on the level of performance it exhibits on whatever task you're having it do.
[ Parent | on HN ]