OpenAI ChatGPT: Optimizing Language Models for Dialogue

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by joe_the_user on Thursday December 01, 2022 @02:04AM (#33813234)

I didn't go into it trying to break or trick it. The only thing tricky about the questions I asked was that I knew the answer to them. I don't think it's necessary dumber than the first page of a Google search but it's certainly not more well informed than that. But it certainly seems smart, which is actually a bit problematic.

[ Parent | on HN ]

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by oefrha on Thursday December 01, 2022 @05:21AM (#33814467)

It’s actually not that different from chatting to the know-it-all type of Internet rando: they can talk to you about anything and seem knowledgeable on all of them, but go into a topic you actually know about and you realize they’re just making shit up or regurgitating myths they read somewhere. You can find that kind of user on HN.

[ Parent | on HN ]

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by andai on Thursday December 01, 2022 @08:33AM (#33815987)

Yeah this is my main concern about GPT-3, there's no truth-fiction slider, and it will often slip complete fabrications into the output, making it dangerous to rely on for real world information. Which is really a shame, because it does actually give great output most of the time.

[ Parent | on HN ]

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by deadpannini on Friday December 02, 2022 @07:42AM (#33829759)

Why is this a special concern about GPT-3? I cannot think of an institution, entity, or tool about which those statements are not true.

Replace "GPT-3" with "Hacker News posters" "Wikipedia", or "News broadcasts" to create three more 100%-accurate paragraphs.

[ Parent | on HN ]

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by dingclancy on Monday December 05, 2022 @03:09AM (#33862826)

I have never seen a human made website with a truth-fiction slider. The answers can be straight up false and scary, but it is no different from other publications out there.

Even with the most credible news sources, it is still up to the person reading it to sense the BS.

[ Parent | on HN ]

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by joenot443 on Thursday December 01, 2022 @09:02AM (#33816292)

It’s a technical preview, not a finished product. If they’d tested it on every combination of Kerouac novels before release, it would probably never see the light of day :) I’m still incredibly impressed.

[ Parent | on HN ]

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by Existenceblinks on Thursday December 01, 2022 @10:29AM (#33817531)

I never believe in natural lang to tell computer to do things with an objective of getting certain result (been skeptical since pre-2011).

It wouldn't be used to fly plane without lots of physical buttons as a fallback.

Composing rigid instructions for computer is already hard, even with precise semantics defined. Even with static typed, dynamic typed, developers will try hard to get rid of a single bug.

AI will serve as a middleware with an objective of arbitrary result.

  Human
  |> UI (request)
  |> AI
  |> UI (response)
  |> Human
  |> UI (request with heuristic)
  |> Computer does thing

[ Parent | on HN ]

Re:OpenAI ChatGPT: Optimizing Language Models for Dialogue by checkyoursudo on Friday December 02, 2022 @08:19AM (#33830079)

Okay, so what is the best race to play as a druid? Now you have to prove that you are not the chatbot, Mr ChatBot.

[ Parent | on HN ]