Resolves YES if GPT-4 is publicly available to be finetuned by 2023-12-21 19:19:00 PST. NO otherwise.
with fine-tuning for GPT-4 coming this fallContext(tweet embed):
Related questions
🏅 Top traders
| # | Name | Total profit |
|---|---|---|
| 1 | Ṁ1,996 | |
| 2 | Ṁ1,328 | |
| 3 | Ṁ389 | |
| 4 | Ṁ329 | |
| 5 | Ṁ308 |
Time to revise my "never bet against OpenAI" heuristic...
From some preliminary results, GPT-4 fine-tuning seems to be much less effective than it was for previous models (possiblity very sensitive to hyperparameters). Also, GPT-4 already follows the system prompt and few-shot examples very well.
Fine-tuning based jailbreaks are still possible despite the new automated dataset moderation that already takes a very long time to process uploads.
"sir the GPUs are melting"
@31ff Anything in the GPT-4 series will count, including GPT-4 Turbo. I applied for GPT-4 finetuning and they outright deleted my application a week later... didn't even reject me, just deleted it. So I would currently resolve this NO.
Arb trading with https://manifold.markets/getby/will-gpt4-finetuning-be-available-b because I predict that whenever they release this, it will either be before Dec21 or after Dec31.
From the announcement today:
GPT-4 fine tuning experimental access
We’re creating an experimental access program for GPT-4 fine-tuning. Preliminary results indicate that GPT-4 fine-tuning requires more work to achieve meaningful improvements over the base model compared to the substantial gains realized with GPT-3.5 fine-tuning. As quality and safety for GPT-4 fine-tuning improves, developers actively using GPT-3.5 fine-tuning will be presented with an option to apply to the GPT-4 program within their fine-tuning console.
@AaronBreckenridge If I get access to GPT-4 finetuning(I'll apply if given the option), or if the public can use finetuned GPT-4 models even if they can't train them, those will definitely count for this market.
A EULA is fine, but if it's strictly b2b(the models can only be used in a non-personal organization) or you need to sign NDAs, that won't count. Has to be available to "non-affiliates" of OpenAI.
If it's partially released to a small group of members of the public, but it's a lucky find like a lootbox in a mobile game, that sounds like NO or resolve it 50%. I'll count it YES if at least the signup form is public, and there are reports of at least some non-affiliates getting access to it.
Not only is there the fact that fine tuning it would be INCREDIBLY slow, GPT-4 has a LOT more capabilities. By the time they released GPT-3.5 finetuning, open source models had almost caught up to GPT-3.5. Allowing people to finetune GPT-4 would have implications that OpenAI themselves probably don't even fully understand yet. The applications that people could find would be both great and terrifying.
@gigab0nus Computing gradients is quadratic in the number of parameters, so we're talking 100x slower. That's a lot slower.
@jonsimon You often don‘t fine-tune the whole network. But yes it will be much slower. If they say so, they will surely find a way to make the fine-tune experience acceptable.
@jonsimon Why couldn't they use something like LoRA to massively save compute? (and also importantly, memory loading multiple versions of the model for inference)
@TomPotter They probably could, but in general it's more practically complicated to add a LoRA adapter, especially for a mixture-of-experts style model like GPT-4.
Not saying it's not doable, but I am saying that you shouldn't expect it to be as straightforward as it is for GPT-3.5
@jonsimon Do you have a source for the quadratic cost of computing gradients? Doesn't backprop have approximately the same time complexity as the forward step?