GPT-4 #5: Will GPT-4 be a dense model?
169
2kṀ280k
resolved Jul 19
Resolved
NO

Conditional on being a transformer.

Nov 25, 11:11pm: Will GPT-4 be a dense model? → GPT-4 #5: Will GPT-4 be a dense model?

  • Update 2025-07-16 (PST) (AI summary of creator comment): The creator has stated they may resolve this market based on the preponderance of evidence, rather than waiting for official confirmation. They have proposed resolving to NO on this basis.

Get
Ṁ1,000
to start trading!

🏅 Top traders

#NameTotal profit
1Ṁ23,912
2Ṁ4,651
3Ṁ4,460
4Ṁ2,611
5Ṁ1,219
Sort by:

It seems unlikely at this point that we'll get any kind of official confirmation by market close. Given that this market and all of the evidence point heavily towards MoE, I want to resolve this NO now. Any objections?

predictedYES

Do these count as yes/no:

An appropriate dense expert is sampled per prompt, so that it's almost dense per-prompt.

ChatGPT-4 is distilled from 8 expert dense models.

GPT-4 base model was trained with 8 models and then only one model is used for ChatGPT-4 with no switching between models.

By GPT-4 do you mean the base model or the RLHF'd chat model called "GPT-4" in the API?

@NoaNabeshima
1. Depends on the sampling procedure. I lean towards resolving a uniform sample with no selection/filtering as yes, any sampling more complex/intelligent than that will probably be no
2. I assume you mean "and ChatGPT-4 is itself dense"? In that case see my answer to 4.
3. See 4, but would resolve YES for ChatGPT-4
4. This question was asked before the distinction between different GPT-4 variants existed. I'm inclined to resolve with based on an OR of all the models since that most closely captures my original intent with the question, but before I decide one way or the other I want to give people a chance to make arguments.

So it's clear: the claims from George Hotz and Soumith Chintala are not sufficient to resolve this market.

predictedNO

"i might have heard the same -- I guess info like this is passed around but no one wants to say it out loud. GPT-4: 8 x 220B experts trained with different data/task distributions and 16-iter inference. Glad that Geohot said it out loud.:"

(https://twitter.com/soumithchintala/status/1671267150101721090)

Apparently none of the people who knew this in advance use Manifold.

I think this means we should slightly downgrade our opinion of the efficiency of prediction markets?

predictedNO

@LoganZoellner lol, the info's been out there for months now, if you know the right twitter users to follow 😉

predictedNO

@rockenots That's my point. If Manifold was an efficient market, even a small number of users who knew the correct answer would quickly push the market to the correct answer due to arbitrage.

But, of course, Manifold is not an efficient market.

@chilli Neither of these people is affiliated with OpenAI

predictedNO

@vluzko Sure, but where there’s smoke there’s fire :) And both of these folks have status in the community and aren’t random folk.

And the beauty of prediction markets is that they don’t need to resolve in order for the market to be convinced that it’s gonna resolve a certain way.

Btw, another Twitter account agreeing with the stated info (https://twitter.com/main_horse/status/1671279346307440640?s=46&t=yqOem5ktaowo8FyJ-ilbzQ)

@chilli I'm not saying you shouldn't bet, I just want it to be clear that I'm not going to resolve the market based on this.

@chilli

Just 500 more so I can reach 50k even

@Gen I’ll buy as much no as you’re willing to stake on yes :)

predictedNO

@Gen Only constraint is my mana balance >:(

@chilli i bet 500 in ur place this time

@chilli You may also want to arbitrage with this one: /Gigacasting/is-gpt4-a-mixture-of-experts

I'm too lazy, I just click buy

predictedYES

Well it's about time some sanity is returning to this market.

I think there is a 90% chance it is dense, but I also think there's a high chance it will never resolve because OpenAI will never tell us.

Edit: So the leaks say it is a mixture, OpenAI being smarter than I expected I guess. That is a bit of a deviation from their previous strategy.

predictedYES

@ShadowyZephyr Agreed, I think it would be better if the end date of the market was continually pushed back until the information was made available. I think the most likely medium term outcome is that the architecture details get leaked through unofficial channels and there is a big controversy around whether it's sufficient to resolve the market.

predictedYES

@jonsimon Right now the close date is 2027. I'm confident we will know before then.

My expectation is that after a year or so information leaks will become more prevalent but right now people working at openAI are probably pretty well taken care of and are happy to see the product they work on explode. After a bit of staff turnover, particularly with them hiring new people en masse, there are bound to be a lot of leaks.

why did this market stop arbing with MoE market?

predictedYES

@Dreamingpast Who knows. I don't think this pair of markets represents the beacon of rational behavior.

© Manifold Markets, Inc.TermsPrivacy