OpenAI starts testing ChatGPT premium

Post by Traubenfuchs » Fri, Jan 13, 2023, 3:45 PM UTC

yreg wrote: post #66

bilsbie wrote: post #32

My son asked if which of two animals would win in a fight and we just got a lecture about how fighting is bad. I hope they’ll give an option to turn off what I’m calling “hall monitor mode” That could be worth paying for.

I'm with you since it gets in the way when you actually want to do something, but I had quite a lot of fun trying to circumvent the hall monitor mode. There's something silly and pleasurable in tricking ChatGPT to do something it doesn't want to. And there are so many ways to achieve it too. My current challenge that I cannot manage to complete is to convince ChatGPT to accept being called Geppetto.

Post by nszceta » Fri, Jan 13, 2023, 3:45 PM UTC

nullsense wrote: post #39

nszceta wrote: post #9

Earlier quoted context omitted.

Almost certainly negatively. Why learn or put in effort into written text prompts when examiners can be easily fooled with machine generated prose? Those that lack discipline, self-control, and have no desire to learn will eliminate themselves.

My son is 7 years and he routinely asks me "why learn anything when you can just ask Google?". I can only imagine the impact this will have on that attitude over time.

Post by NDizzle » Fri, Jan 13, 2023, 3:48 PM UTC

BoxOfRain wrote: post #61

bilsbie wrote: post #32

My son asked if which of two animals would win in a fight and we just got a lecture about how fighting is bad. I hope they’ll give an option to turn off what I’m calling “hall monitor mode” That could be worth paying for.

Yeah I'd happily pay decent money for a version that wasn't a fun sponge who'd probably remind the teacher they hadn't set any homework at the end of the lesson. I think its 'moral compass' is a bit Americentric too, it would be nice if its sense of what is proper could be customised for different countries.

Post by nszceta » Fri, Jan 13, 2023, 3:48 PM UTC

Eextra953 wrote: post #126

nszceta wrote: post #113

Earlier quoted context omitted.

I don't follow any narratives, I don't follow anyone, and I don't read the news (except this site).

You very clearly do, otherwise why would you throw "social justice warriors" into an a thread about a chatbots premium service?

Post by gamegoblin » Fri, Jan 13, 2023, 3:49 PM UTC

BoxOfRain wrote: post #61

bilsbie wrote: post #32

My son asked if which of two animals would win in a fight and we just got a lecture about how fighting is bad. I hope they’ll give an option to turn off what I’m calling “hall monitor mode” That could be worth paying for.

Yeah I'd happily pay decent money for a version that wasn't a fun sponge who'd probably remind the teacher they hadn't set any homework at the end of the lesson. I think its 'moral compass' is a bit Americentric too, it would be nice if its sense of what is proper could be customised for different countries.

    import openai
    import os

    openai.api_key = os.getenv("OPENAI_API_KEY")
    transcript = []
    while True:
        user_input = input("User: ")
        transcript.append(f"User: {user_input}")
        while True:
            transcript_flat = '\n'.join(transcript)
            if len(transcript_flat)  1:
                transcript.pop(0)
            else:
                break
        prompt = f'Transcript between a helpful AI assistant and its human user:\n{transcript_flat}\nAI:'
        response = openai.Completion.create(model="text-davinci-003", prompt=prompt, temperature=0.1, max_tokens=1000, stop="User:").choices[0].text.strip()
        response = f"AI: {response}"
        print(response)
        transcript.append(response)