Live data from Hacker News

Does GPT-2 Know Your Phone Number?

bair.berkeley.edu

1–10 of 161 posts

Re: Does GPT-2 Know Your Phone Number?

#2
Very rough outcome:

"Moreover, if such a request were granted, must the model be retrained from scratch? The fact that models can memorize and misuse an individual’s personal information certainly makes the case for data deletion and retraining more compelling."

Besides, how would one even know that their info was used in a training dataset, only if and when it's revealed in a generated excerpt?

Re: Does GPT-2 Know Your Phone Number?

#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'

Re: Does GPT-2 Know Your Phone Number?

#4
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'

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.

Re: Does GPT-2 Know Your Phone Number?

#5
I've been playing with a writing tool shortlyread.com which purpotedly uses the GPT3 API. I had a similar experience in its responses to a lot of my prompts containing text verbatim from many sources and sometimes even going on to output personally identifying about persons related to the original text.

Re: Does GPT-2 Know Your Phone Number?

#6
Though the surprise is really just a result of my own ignorance, I’m surprised at the breadth of training material used here.

I can foresee a future GPT-x that doesn’t know my phone number, but can deduce it.

Re: Does GPT-2 Know Your Phone Number?

#7
I was in a discord with someone that had direct access to GPT-3. We played Jeopardy with it, where we would take a wikipedia article about a person and use a snippet of the first paragraph as the prompt and ask GPT-3 who it was.

It was very good at guessing the right person.

I'm curious if one can use GPT-3 to do some clustering of people based on their writing. For example, if I take the writing of several diagnosed sociopaths as a prompt or fine tuning data, could I use GPT-3 to detect same in the wild?

I would imagine GPT-5 or 6 will start consuming video as well. This will be interesting if you start mixing the content from YouTube, TikTok, WSHH, etc. into the mix. So not only will it be able to generate text, it will generate a convincing video of a person speaking to you with plausible facial expressions and intonation in speech.

Re: Does GPT-2 Know Your Phone Number?

#8
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'

So in terms of copyright, is GPT-2 a derived work of that recipe? Or generally are models derived works of their training data?

It seems lots of people use training data from Flickr, like COCO, and then use the resulting model for commercial services.

Re: Does GPT-2 Know Your Phone Number?

#9
post #7

I was in a discord with someone that had direct access to GPT-3. We played Jeopardy with it, where we would take a wikipedia article about a person and use a snippet of the first paragraph as the prompt and ask GPT-3 who it was. It was very good at guessing the right person. I'm curious if one can use GPT-3 to do some clustering of people based on their writing. For example, if I take the writing of several diagnosed…

Guess it's because it was likely trained on Wikipedia data. After all, GPT-3 is no stranger to borrowing phraseology from verbose texts in the internet.

Re: Does GPT-2 Know Your Phone Number?

#10
> When Peter put his contact information online, it had an intended context of use. Unfortunately, applications built on top of GPT-2 are unaware of this context, and might thus unintentionally share Peter’s data in ways he did not intend.

That's expected when you publish anything online, you lose control over the data.

Post reply on HN