Hacker News Reader

Comment by narrator | Hacker News Reader

It's funny how they never release the model. I guess they are scared of spammers, 4chan or worse, the Russians. This is the harbinger of the future, isn't it? Technology that's too powerful to be widely deployed is kept under lock and key by priests who deal in secret knowledge only available to the properly initiated.

View on HN

Give it a few days and lucidrains will have the code up[0].

But in honesty, it is probably how people react. We saw this with Pulse, GPT, and many others. The authors are clear about the limitations but people talk it up too much and others shit on it. There's also a reproducibility crisis in ML (many famous networks, like Swin[1][2][3], can't be reproduced (even worse when reviewers concentrate on benchmarks)). It isn't like many can train a model like this anyways. It gives them benefit of the doubt and maintains good publicity rather than controversial.

Of course, this is extremely bad from an academic perspective and personally I believe you should have your paper revoked if it isn't reproducible. You'd be surprised how many don't track the random seed or measure variance. We have GitHub. You should be able to write training options that get approximately the same results as the paper. Otherwise I don't trust your results.

[0] https://github.com/lucidrains/parti-pytorch

[1] https://github.com/microsoft/Swin-Transformer/issues/183

[2] https://github.com/microsoft/Swin-Transformer/issues/180

[3] https://github.com/microsoft/Swin-Transformer/issues/148

I really doubt that the motivation for not publishing the model for "turns text into trippy images" is "it's too powerful to trust the world with it" vs banal business reasons.

The claimed reason for not publishing the model in TFA:

> This leads such models, including Parti, to produce stereotypical representations of, for example, people described as lawyers, flight attendants, homemakers, and so on...

> Models which produce photorealistic outputs, especially of people, pose additional risks and concerns around the creation of deepfakes.

> ...the range of outputs from a model is dependent on the training data, and this may have biases toward Western imagery and further prevent models from exhibiting radically new artistic styles...

> For these reasons, we have decided not to release our Parti models, code, or data for public use without further safeguards in place.

So maybe they're partly afraid that it's too powerful, but even moreso they are afraid it's too white.

Rather, I think they're afraid of the criticism they'll face over such biases if they make the model generally available.

It doesn't take much imagination to see these issues being used by AI opponents as justification to ban or heavily regulate machine learning research.

Eh, the cost of training is already within the reach of wealthy individuals, and as better TPUs/GPUs appear on the cloud cost drops.

This is definitely going to become commonly available tech this decade.

The training cost of state of the art models has been increasing every year for the last 10 years. I don’t see any indication this will change in the near future.

The parts of the model and how to go about training it are well known (i.e VIT VQGAN, auto-regressive transformers etc). They also use LAION-400 for training which is an open source dataset. Can be replicated, but will take time, patience and compute.

This is not true for some of the other recent headline papers: DALL-E2, PALM, Imagen etc. datasets are the primary deterrent, model details are well known.

Reply on news.ycombinator.com