[HenryMulligan]

Ignoring what this model architecture could do and just considering what this model does do, why would I (or anyone) want to run this model (locally) to do <insert use-case>? Is it entirely a proof-of-concept for future training on medical data? Are they looking to use this to attempt to ethically justify training on (free-tier) user's personal data via the application of noise to the training data?

[malfist]

You can hide that you pirated content for training

[astrange]

You can't hide that. You can't use technical measures to hide from discovery.

I think an entire book is a little too large to mask with this method and still end up learning anything.

[faangguyindia]

U can avoid book publisher lawsuit which Anthropic is dealing with using this approach

[porridgeraisin]

It's the last option.

The whole framing of DP is:

Probability that you reveal private info is same whether or not you train on a particular users data.

It is useful in many cases, but google the product company specifically is going to use it for ads.

[floridianfisher]

The purpose is research