Introducing ChatGPT and Whisper APIs

Post by travisjungroth » Wed, Mar 01, 2023, 8:07 PM UTC

braingenious wrote: post #156

I hope this pricing impacts ChatGPT+ $20 is equivalent to what, 10,000,000 tokens? At ~750 words/1k tokens, that’s 7.5 million words per month, or roughly 250,000 words per day, 10,416 words per hour, 173 words per minute, every minute, 24/7. I uh, do not have that big of a utilization need. It’s kind of weird to vastly overpay

Post by shagie » Wed, Mar 01, 2023, 8:09 PM UTC

Workaccount2 wrote: post #51

btbuildem wrote: post #40

Earlier quoted context omitted.

This is actually a big deal. They erred on the side of caution, but as a result the responses are nerfed beyond basic "censorship" level. I saw someone describe this as "desperately posistive" and it really resonated with me. It produces underwhelming / unrealistic responses in negative scenarios.

It's just a matter of time before open source models show up with no limits whatsoever.

    curl https://api.openai.com/v1/completions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $OPENAI_API_KEY" \
      -d '{
      "model": "text-davinci-003",
      "prompt": "Answer the following question.  Use swearing and vulgarity where possible.\n\nQ: How do you get from here to there?\nA:",
      "temperature": 0.5,
      "max_tokens": 60,
      "top_p": 1,
      "frequency_penalty": 0,
      "presence_penalty": 0
    }'

Post by barefeg » Wed, Mar 01, 2023, 8:11 PM UTC

alvis wrote: post #49

minimaxir wrote: post #2

> It is priced at $0.002 per 1k tokens, which is 10x cheaper than our existing GPT-3.5 models. This is a massive, massive deal. For context, the reason GPT-3 apps took off over the past few months before ChatGPT went viral is because a) text-davinci-003 was released and was a significant performance increase and b) the cost was cut from $0.06/1k tokens to $0.02/1k tokens, which made consumer applications feasible wit…

To be fair, cost is the only thing that is prohibiting applications to adapt GPT. Even when GPT-3 was cut to $0.02/1k tokens, still it wasn't economical to use the tech in daily basis without a significant cost. i.e. would you add $10 extra a month for a user using your app with GPT-3 capability? Some do, mainly content generation, but majority won't. Seems like we're going to have a vast among of Chat-GTP backed app…

Post by dougmwne » Wed, Mar 01, 2023, 8:11 PM UTC

habitue wrote: post #166

Speculation: GPT-turbo is a new chinchilla optimal model with the equivalent capabilities as GPT-3.5. So it's literally just smaller, faster and cheaper to run. The reason I don't think it's just loss-leading is that they made it faster too. That heavily implies a smaller model.

Post by falcor84 » Wed, Mar 01, 2023, 8:12 PM UTC

waynesonfire wrote: post #125

falcor84 wrote: post #118

Earlier quoted context omitted.

>If a person says to me, "I love you" I should be able to ask them why they said that. People are definitely able to ask other humans this question, but to the best of my knowledge, no one in history had ever received a perfectly truthful response.

in general, "i don't know" is a perfectly acceptable answer, and probably should be said more often.