top | item 38499575

How Googlers cracked OpenAI's ChatGPT with a single word

31 points| theduder99 | 2 years ago |sfgate.com

50 comments

order

Jimmc414|2 years ago

I reported this behavior 4 months ago on HN https://news.ycombinator.com/item?id=36675729

[The researchers wrote in their blog post, “As far as we can tell, no one has ever noticed that ChatGPT emits training data with such high frequency until this paper. So it’s worrying that language models can have latent vulnerabilities like this.”]

catchnear4321|2 years ago

it is worrying just how much of this has shown up in hn comments months before being officially discovered by official experts.

mike_hearn|2 years ago

I'm not sure how this is an attack. Is it actually vital that models don't repeat their training data verbatim? Often that's exactly the answer the user will want. We are all used to a similar "model" of the internet that does that: search engines. And it's expected and required that they work this way.

OpenAI argue that they can use copyrighted content so repeating that isn't going to change anything. The only issue would be if they had used stolen/confidential data to train on, and it was discovered that way, but it also seems unlikely anyone could easily detect that given that there'd be nothing to intersect it with, unlike in this paper.

The blog post seems to slide around quite a bit, roving from "it's not surprising to us that small amounts of random text is memorized" straight to "it's unsafe and surprising and nobody knew". The nobody knew idea, as Jimmc414 has nicely proven in this thread, is false alarm because their technique actually was detected and the paper authors just didn't know that it had been. And "it's unsafe" doesn't make any sense in this context. Repeating random bits of memorized text surrounded by huge amounts of original text isn't a safety problem. Nor is it an "exploit" that needs to be "patched". OpenAI could ignore this problem and nobody would care except AI alignment researchers.

The culture of alarmism in AI research is vaguely reminiscent of the early Victorians who argued that riding trains might be dangerous, because at such high speeds the air could be sucked out of the carriages.

somat|2 years ago

Speaking of remembering training data, I see that as a big problem with chat based systems. They swallow a bunch of data, then generate something when prompted, My worry is not so much copyright infringement but more something like citation needed?

Has anyone done any work to produce citations for the generated data?

FartyMcFarter|2 years ago

This should make companies think twice about what training data they use. Plausible deniability doesn't work if you spit out your training data verbatim.

cedws|2 years ago

What's the endgame of this "AI models are trained on copyrighted data" stuff? I don't see how LLMs can work going forward if every copyright owner needs to be paid or asked for permission. Do they just want LLM development to stop?

sanp|2 years ago

Why should LLM development proceed if the only way it can is by violating copyright?

krapp|2 years ago

Either buy rights to the data, produce training data for which you own the rights or use copyright-free data. Those options exist, but no one takes advantage of them because none of them are as much of a "free money machine" as just ripping off as many people as possible to homogenize and commodify their work.

If LLM development can't continue without violating copyright then that makes it clear that the purpose of LLM development is violation of copyright. Which is something we all already knew but it's nice to have it spelled out in no uncertain terms.

souplesse|2 years ago

Is your argument that the ends justify the means?

TillE|2 years ago

We're talking about multi-billion dollar companies with the potential to become truly enormous, I have no doubt that they can cut appropriate deals with large publishers.

Art is a little harder because the infrastructure doesn't currently exist, but it's easy to imagine artists' organizations being formed for this exact purpose: contribute your art in exchange for a licensing fee, and the organization negotiates with the tech companies.

science4sail|2 years ago

> I don't see how LLMs can work going forward if every copyright owner needs to be paid or asked for permission.

Simple, LLM development leadership shifts to open-source models and/or organizations/countries that are willing to bend or ignore copyright law. Silicon Valley isn't the world, neither is the United States.

hooverd|2 years ago

It's moreso copyright for me but not for thee.

Jimmc414|2 years ago

What proof is there that copyrighted data was used? Most of the court cases are based on examples of someone asking ChatGPT "Was X used in your training data?" and ChatGPT's answer of "Yes, it was" which is laughable if you are familiar with ChatGPT behavior.

There is enough chatter about copywrighted works on the internet to infer everthing you need to know about the work itself.

gardenhedge|2 years ago

I think as part of AI regulations, all companies should have to publish their training data along side their model.