News for hackers. Stuff that matters.
Re:OpenAI makes ChatGPT 'more direct, less verbose' by eastoeast on Thursday April 11, 2024 @11:27PM (#40009128)
I feel they've leaned too far in one direction, and will (hopefully) adjust behavior again soon.

E.g. "Create a list of 20 potential names for a startup about Ovens"

Chatgpt returned only a single response to this. When prompted for 10 more options, it only return two new options. Seems it is forcing itself not to count properly to satisfy brevity requirements.

Re:OpenAI makes ChatGPT 'more direct, less verbose' by tus666 on Thursday April 11, 2024 @11:47PM (#40009214)
The more I use ChatGPT, the useless I realize it is.

It looks impressive at first, until you realize it is like a trick pony. Don't get it to haul your luggage.

It gives apparently good summaries of sometimes complex topics. But then you ask it to explain things in more detail...welcome to a special hell of circular reasoning, inherent contradictions, and surprising about-faces that occur even when you ask a complementary question (complementary as in congruent not admiring).

ChatGPT: <long verbose answer...>

Me: Oh so your saying X implies Y but not Z? (which previous answer did)

ChatGPT: Apologies for causing confusion, I misspoke.... (go on to give a worse response now)

Me: But your first response was OK, I just wanted to clarify XYZ...

ChatGPT: <now gives a response with directly conflicting statements>

How many times have you seen this?

Re:OpenAI makes ChatGPT 'more direct, less verbose' by Jimmc414 on Thursday April 11, 2024 @11:15PM (#40009084)
Interesting that MMLU and HumanEval scores dropped slightly.