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

Does GPT-2 Know Your Phone Number?

bair.berkeley.edu

Post reply on HN
Print view View original

141–150 of 161 posts

Re: Does GPT-2 Know Your Phone Number?

#141

Post by alisonkisk »

boulos wrote: post #100
kevinmchugh wrote: post #27

Earlier quoted context omitted.

Recipes aren't typically copyrightable In general, I think the question is unsettled

The “recipe” itself (the ingredients, the steps) isn’t copyrightable but the surrounding text of a “recipe” can be considered copyrightable. So you can happily reproduce the statements of facts and the process. You can’t include someone’s anecdotes about how their grandfather liked to make the dish for New Year’s Eve.

It ambiguous whether the directions are copyrightable. The less useful and more literary the directions are, the more copyrightable. But paraphrasing to extract the technical useful directions escapes infringement.

https://www.copyright.gov/help/faq/faq-protect.html

Re: Does GPT-2 Know Your Phone Number?

#142

Post by alisonkisk »

colanderman wrote: post #28
newman8r wrote: post #3

Playing with the AI dungeon a while back (on the GPT-2 mode) I was presented with a tilapia recipe, titled "Kittencal's Broiled Tilapia" - it sounded bizarre so I decided to do a google search and I found that it was directly pulled from from https://www.recipezazz.com/recipe/broiled-parmesan-tilapia-7... - the user who posted it was 'Kittencal'

This is something that has repeatedly bothered me while playing with GPT-2. It retains too much "long-tail" knowledge that seems counterproductive for a generic language tool. I would think those one-off associations should not be present after training has "digested" them but there they are.

It's over fitting, not long tail, that is the problem. It ends up copying input instead of analyzing and synthesizing.

Re: Does GPT-2 Know Your Phone Number?

#143

Post by LdSGSgvupDV »

geofft wrote: post #107
fouronnes3 wrote: post #4

Earlier quoted context omitted.

There is enough GPT discussion online now that the next language model will be trained on text that talks about itself. That's when it gets interesting.

This seems like what xkcd called "citogenesis" - something inaccurate gets published on Wikipedia, a traditional "reliable source" (newspaper, published nonfiction book, etc.) retells that bit of information without a source, Wikipedia cites the source, that information is now firmly established as truth for the rest of humanity. I worry about this with Google's language translation models, too. It's entirely possibl…

Sounds like a kind of cyber-meme?

Re: Does GPT-2 Know Your Phone Number?

#144

Post by alisonkisk »

ben_w wrote: post #48
hyperpape wrote: post #42

Earlier quoted context omitted.

Of course it isn't how the human mind works. You can ask a person "did you come up with that sentence, or is it something you read?" And they can answer that question. The answer isn't perfectly reliable, but it isn't completely unreliable either. You can't do that with GPT-2/GPT-3. Big picture: the human mind is a machine of sorts. It's not the same kind of machine as any form of machine learning we've developed so…

> The answer isn't perfectly reliable, but it isn't completely unreliable either. How would we be able to tell how reliable it is in general? """The left brain of people whose hemispheres have been disconnected has been observed to invent explanations for body movement initiated by the opposing (right) hemisphere, perhaps based on the assumption that their actions are consciously willed.""" - https://en.wikipedia.org…

The point is that humans have a basic ability to make specific coherent observations about themselves and the world. GPT can't do that except occasionally by accident in the middle of a muddle.

Re: Does GPT-2 Know Your Phone Number?

#145

Post by stubish »

"When Peter put his contact information online, it had an intended context of use"

That is a great way of thinking of it. Lots of information, particularly from 90s and 00s, got put up on the 'Net with no intention of it being archived in perpetuity for public consumption and used for unintended purposes.

Re: Does GPT-2 Know Your Phone Number?

#146

Post by why_only_15 »

max_ wrote: post #134
why_only_15 wrote: post #72

Earlier quoted context omitted.

In practice you add large gaussians to the deltas, which gives you reasonably strong guarantees.

How is the strength of these gurantees quantified? Any resources?

This is what I remember from working closely with the people doing this at Apple. I believe they may have published a paper, but I'm not sure. Vojta Jina was the relevant manager.

Re: Does GPT-2 Know Your Phone Number?

#147

Post by why_only_15 »

est31 wrote: post #137
why_only_15 wrote: post #72

Earlier quoted context omitted.

In practice you add large gaussians to the deltas, which gives you reasonably strong guarantees.

It's a common fallacy. Adding noise does not anonymize data sufficiently. If your traffic monitoring software adds gaussians to car speeds, you can still average over multiple reports about two cars to identify their respective average speeds. Those can be used to determine whether they are trucks or cars, etc. In neural networks, weight changes do carry meaning. If your network has particularly large updates for the…

This isn't about averaging over all your submissions, it's about averaging over the entire population (in this case, of iphone users, ~1,000,000,000). Data about the entire population, e.g. how many people click this button, or how many results do most people get from this page, or what kind of things do people take pictures of, i think are safe.

Re: Does GPT-2 Know Your Phone Number?

#149

Post by est31 »

why_only_15 wrote: post #147
est31 wrote: post #137

Earlier quoted context omitted.

It's a common fallacy. Adding noise does not anonymize data sufficiently. If your traffic monitoring software adds gaussians to car speeds, you can still average over multiple reports about two cars to identify their respective average speeds. Those can be used to determine whether they are trucks or cars, etc. In neural networks, weight changes do carry meaning. If your network has particularly large updates for the…

This isn't about averaging over all your submissions, it's about averaging over the entire population (in this case, of iphone users, ~1,000,000,000). Data about the entire population, e.g. how many people click this button, or how many results do most people get from this page, or what kind of things do people take pictures of, i think are safe.

If you average over the entire population, it's privacy preserving indeed. But this averaging happens on the side of the server, not the client, so I can't really verify whether the server stores away the deltas of interesting/all users or it averages really all user deltas. I know apple has some means to anonymize users by using random changing IDs instead of the apple ID, but they can correlate it to an apple ID via the ip address or other means.

Re: Does GPT-2 Know Your Phone Number?

#150

Post by headbansown »

px43 wrote: post #19

I've been saying this for years, but every post you make online, every unencrypted email, IM, text message, etc, will eventually end up getting sold off as training data for future machine learning projects. Every company stores this stuff for ages, and the value of candid conversation data just keeps increasing. Eventually these companies are either going to get hacked, get bought, or go bankrupt, and all the cleart…

"If one would give me six lines written by the hand of the most honest man, I would find something in them to have him hanged."

-- Richelieu

Post reply on HN