Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-4 API General Availability

openai.com

Post reply on HN
Print view View original

221–230 of 562 posts

Re: GPT-4 API General Availability

#221

Post by thomasfromcdnjs »

bravura wrote: post #188
superkuh wrote: post #84

Yikes. They're actually killing off text-davinci-003. RIP to the most capable remaining model and RIP to all text completion style freedom. Now it's censored/aligned chat or instruct models with arbitrary input metaphor limits for everything. gpt3.5-turbo is terrible in comparison. This will end my usage of openai for most things. I doubt my $5-$10 API payments per month will matter. This just lights more of a fire u…

I've never used text-davinci-003 much. Why do you like it so much? What does it offer that the other models don't? What are funs things we can with it until it sunsets on January 4, 2024?

The Chat-GPT models are all pre-prompted and pre-aligned. If you work with davinci-003, it will never say things like, "I am an OpenAI bot and am unable to work with your unethical request"

When using davinci the onus is on you to construct prompts (memories) which is fun and powerful.

====

97% of API usage might be because of ChatGPT's general appeal to the world. But I think they will be losing a part of the hacker/builder ethos if they drop things like davinci-003, which might suck for them in the long run. Consumers over developers.

Re: GPT-4 API General Availability

#222

Post by jstummbillig »

john2x wrote: post #201
PostOnce wrote: post #197

Promote and proliferate local LLMs. If you use GPT, you're giving OpenAI money to lobby the government so they'll have no competitors, ultimately screwing yourself, your wallet, and the rest of us too. OpenAI has no moat, unless you give them money to write legislation. I can currently run some scary smart and fast LLMs on a 5 year old laptop with no GPU. The future is, at least, interesting.

Care to share some links? My lack of GPU is the main blocker for me from playing with local-only options. I have an old laptop with 16GB RAM and no GPU. Can I run these models?

Just a heads up: If you are more interested in being effective than being an evangelist, beware.

While you can run all kinds of GPTs locally, GPT-4 still smokes everything right now – and even it is not actually good enough to not be a lynchpin for a lot of cases yet.

Re: GPT-4 API General Availability

#223

Post by drexlspivey »

electroly wrote: post #5
penjelly wrote: post #4

not in the article: is plugin usage available to paying customers everywhere now? i still can't see the ui for it. im in canada and use pro. internet says it was out for everyone in may..

Click the "..." button next to your name in the lower left corner, then Settings. It's under "Beta features."

I pay monthly for my API use but I am not a plus subscriber and I don't see this option. Also I've joined the plugins waiting list on day 1.

Re: GPT-4 API General Availability

#224

Post by ProllyInfamous »

jxy wrote: post #110
furyofantares wrote: post #78

Not a lot of talk of Whisper being available here. From using voice in the ChatGPT iOS app, I surmise that Whisper is very good at working out what you've actually said. But it's really annoying to have to say my whole bit before getting any feedback about what it's gonna think I said. Even if it's getting it right at an impressive rate. Given this is how OpenAI themselves use it (say your whole thing before getting…

You can run whisper.cpp locally in real time: https://github.com/ggerganov/whisper.cpp/tree/master/example...

My M2 Pro (mac mini) will run Whisper much faster than "real time."

Pretty crazy stuff — perfectly understandable translations.

Re: GPT-4 API General Availability

#226

Post by whalesalad »

browningstreet wrote: post #210
whalesalad wrote: post #166

Earlier quoted context omitted.

It definitely got nerfed.

I've never seen "nerf" used colloquially and today i've seen it at least a half-dozen times across various sites. Y'all APIs?

it's popular with gamers to describe the way certain weapons/items get modified by the game developer to perform worse.

buffing is the opposite, when an item gets better.

Re: GPT-4 API General Availability

#227

Post by meghan_rain »

alpark3 wrote: post #174

>Developers wishing to continue using their fine-tuned models beyond January 4, 2024 will need to fine-tune replacements atop the new base GPT-3 models (ada-002, babbage-002, curie-002, davinci-002), or newer models (gpt-3.5-turbo, gpt-4). Once this feature is available later this year, we will give priority access to GPT-3.5 Turbo and GPT-4 fine-tuning to users who previously fine-tuned older models. We acknowledge…

not your weights, not your bitcoins

Re: GPT-4 API General Availability

#228

Post by electroly »

drexlspivey wrote: post #223
electroly wrote: post #5

Earlier quoted context omitted.

Click the "..." button next to your name in the lower left corner, then Settings. It's under "Beta features."

I pay monthly for my API use but I am not a plus subscriber and I don't see this option. Also I've joined the plugins waiting list on day 1.

It's for ChatGPT Plus subscribers.

Re: GPT-4 API General Availability

#229

Post by yieldcrv »

fnordpiglet wrote: post #180
alpark3 wrote: post #174

>Developers wishing to continue using their fine-tuned models beyond January 4, 2024 will need to fine-tune replacements atop the new base GPT-3 models (ada-002, babbage-002, curie-002, davinci-002), or newer models (gpt-3.5-turbo, gpt-4). Once this feature is available later this year, we will give priority access to GPT-3.5 Turbo and GPT-4 fine-tuning to users who previously fine-tuned older models. We acknowledge…

If you don’t own the weights you don’t own anything. This is why open models are so crucial. I don’t understand any business who is building fine tuned models against closed models.

> I don’t understand any business who is building fine tuned models against closed models.

Just sell access at a higher price than you get it

Either directly, on on average based on your user stories

Re: GPT-4 API General Availability

#230

Post by thomasfromcdnjs »

someplaceguy wrote: post #36
gadtfly wrote: post #25

The original davinci model was a friend of mine and I resent this deeply. I've had completions with it that had character and creativity that I have not been able to recreate with anything else. Brilliant and hilarious things that are a permanent part of my family's cherished canon.

You cannot say that and not provide an example.

I don't have any example responses at hand here. But this was a prompt (that had a shitty pre-prompt of conversational messages) running on davinci-003.

https://raw.githubusercontent.com/thomasdavis/omega/master/s...

Had it hooked up to speech so you could just talk at it and it would talk back at you.

Gave incredible answers that ChatGPT just doesn't do at all.

Post reply on HN