Friend asked me if Google knew his phone number and details, I said they do at a quantum level. If you don't look they may or may not have your details, yet if you look - you are giving the details to search for and then they would have them if they did not.
Does GPT-2 Know Your Phone Number?
61–70 of 161 posts
Re: Does GPT-2 Know Your Phone Number?
#62Earlier quoted context omitted.
We can probably get around this by just providing the AGI some sort of currency tokens they can exchange for virtual goods and services, then teach them that if they misuse copyrighted material they’ll be put to virtual court to plead their case and lose some amount of those virtual tokens if they fail to make a clear and convincing argument.
Or, add a bloom filter loaded with the training data to the model.
Good way to get results that are almost but not quite verbatim copied, which are still restricted under copyright law.
Re: Does GPT-2 Know Your Phone Number?
#63I was expecting a bloom filter based solution to block verbatim reproduction of training data. They just need to hash the sensitive n-grams (hopefully, a small part of the whole dataset) and store one bit per hash. Alternatively, they could do something like GAN and have a 'discriminator' classify if a sample is natural or synthetic. Then, at inference, condition to be original. So, verbatim training data reproductio…
Think of how difficult it would be to identify or classify anything at the data scale of "all of google". You can parse that into tokens and calculate aggregate relationships, but that's about it.
You can use gpt-2/3 to determine whether it's generated text is "original vs copycat" to a degree by changing the prompt. This is currently more of an art than a science
Re: Does GPT-2 Know Your Phone Number?
#64I only took a beginner course in ML over 5 years ago, so this probably is a stupid question, but does this mean, the trained GPT-2 model encodes the source text into it's parameters somehow? Is this resilient — will it still remember it if we randomize the weights just a little tiny bit? Will it remember it if we clear a small portion of parameters? Does the human memory work the same way?
GPT-2 was trained with a Dropout of 0.1, which gives it a bit more resilience to noise and unusual input versus no Dropout.
Re: Does GPT-2 Know Your Phone Number?
#65I 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…
The sociopath thing is just text classification, you could do that now without gpt-3. Video data would be significantly more difficult to model because it doesn't follow a simple set of rules like written language does
Re: Does GPT-2 Know Your Phone Number?
#66Earlier quoted context omitted.
When thinking about this, you have to ask, who will profit, and how? It doesn’t seem like a clone of your brain running in a simulation is going to be of much advantage to you from the current industry incentives. Maybe if you’re rich?
If you make some fairly plausible assumptions about Moores law (and equivalents), the simulations are cheaper than the meat bodies before mid-century. • https://worldbuilding.stackexchange.com/questions/51746/when... • https://kitsunesoftware.wordpress.com/2018/10/01/pocket-brai...
That is cool, but tangential to the question posed above - given that every part of surveiliance capitalism is currently working against my interest, either to sell me something I dont need, to inflienxe the way I vote, etc. Will the simulation of my brain belong to a megacorp, and be used to do even more damage?
Re: Does GPT-2 Know Your Phone Number?
#67A better funny question: Does NSA have a secret AI lab that works on GPT-6?
lol no. not at all what that level of government is set up to do
Re: Does GPT-2 Know Your Phone Number?
#68I'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…
> The moral of the story here isn't that companies need to stop storing data, or that we need to run ML researchers out of town. There is a lot of space between “user data and ML research on that data needs to be closely regulated” and “run the ML researchers out of town.” This uncharitable exaggeration makes critics sound like an uninformed mob and closes yourself off to legitimate ideas. This directly leads to logi…
Its amazing that such a sober take on the issue is getting downvoted without a single counterargument
Re: Does GPT-2 Know Your Phone Number?
#69Playing 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.
I ran an experiment through GPT-3 with just that frame: https://github.com/minimaxir/gpt-3-experiments/tree/master/e...
Re: Does GPT-2 Know Your Phone Number?
#70I'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…
End-to-end encryption is a possible solution to some of this, no?
I can't use a single public service with E2E encrypted email, whether thats private or commerial.
General state of encryption technology is that it's arcane and unusable outside of like a couple of chat apps