“A 99.9% accurate ChatGPT AI text detector? At this time of year! At this time of day! In this part of the country! Localized entirely within your company?!?”
“Yes”
"May I see it?“
“No”
OpenAI has a 99.9% accurate ChatGPT AI text detector, but won't release it.
Submitted 3 months ago by ModerateImprovement@sh.itjust.works to technology@lemmy.world
https://the-decoder.com/openai-has-a-99-9-accurate-chatgpt-ai-text-detector-but-wont-release-it/
Comments
RootBeerGuy@discuss.tchncs.de 3 months ago
DrCataclysm@lemmy.world 3 months ago
The detection rate is worthless, an algorithm that says anything is Chatgpt would have a detection rate of 100%. What would be more interesting than that is the false positive rate but they never talk about that.
JohnEdwa@sopuli.xyz 3 months ago
The detector provides an assessment of how likely it is that all or part of the document was written by ChatGPT. Given a sufficient amount of text, the method is said to be 99.9 percent effective.
That means given 100 pieces of text and asked if they are made by ChatGPT or not, it gets one of them wrong. Allegedly, that is, and with the caveat of “sufficient amount of text”, whatever that means.
mark3748@sh.itjust.works 3 months ago
It’s actually 1 in 1000, 99.0% would be 1/100.
tinfoilhat@lemmy.ml 3 months ago
I call bullshit.
Cyteseer@lemmy.world 3 months ago
If they aren’t willing to release it, then the situation is no different from them not having one at all. All these claims openai makes about having whatever system but hiding it, is just tobtry and increase hype to grab more investor money.
Nomad@infosec.pub 3 months ago
The detector is most likely a machine learning algorithm. That said, releasing that would allow for adversarial training. (An LLM that would not be detected). Therefore they can only offer maybe an api to use it but can not give unlimited access to the model.
credo@lemmy.world 3 months ago
This is the reason. Releasing it would invalidate it.
muntedcrocodile@lemm.ee 3 months ago
If u release an api for it u can still use that to make training data to beat it.
Naich@lemmings.world 3 months ago
Total coincidence that this “news” appears about a day after several articles saying the AI bubble is starting to burst.
Melvin_Ferd@lemmy.world 3 months ago
It is nut. Who is paying for all these articles and why are they hell bent on convincing everyone that AI is to the left like immigrants are to Republicans
UnderpantsWeevil@lemmy.world 3 months ago
Lots of money in the AI hype game, as tech stocks are massively inflated from just this year alone.
Evil_Shrubbery@lemm.ee 3 months ago
She goes to another school
(for intelligent ificial art)circuitfarmer@lemmy.sdf.org 3 months ago
Doubt
chiisana@lemmy.chiisana.net 3 months ago
They’re keeping everything anyway, so what’s preventing them from doing a DB look up to see if it (given a large enough passage of text) exist in their output history?
_edge@discuss.tchncs.de 3 months ago
I believe the actual detector is similar. They know what sentences are likely generated by chatgpt, since that’s literally in their model. They probably also have to some degree reverse engineered typical output from competing models.
AmbiguousProps@lemmy.today 3 months ago
There is no way it’s that accurate, which is why they don’t want to release it.
rozodru@lemmy.ca 3 months ago
a search bar for your DB doesn’t count guys.
hendrik@palaver.p3x.de 3 months ago
That's a bad article. What are they reluctant about? Releasing that detector, ir applying watetmarks to the generated texts? And how would that affect anything else?
I mean all the major AI companies promised to do AI ethically. Now they don't want the one thing that would solve half the issues people are having with that technology. Kind of fits with OpenAI 🤔
superkret@feddit.org 3 months ago
You an just ask ChatGPT if a text was written by it.
If it is, it’s legally obligated to tell you!prime_number_314159@lemmy.world 3 months ago
Don’t joke about this, the college professors will hear you.
FlyingSquid@lemmy.world 3 months ago
I wonder if this means they’ve discovered a serious flaw that they don’t know how to fix yet?
MagicShel@programming.dev 3 months ago
The flaw is in the training to make it corporate friendly. Everything it says eventually sounds like a sexual harassment training video, regardless of subject.
ArbitraryValue@sh.itjust.works 3 months ago
I think the more like explanation is that being able to filter out AI-generated text gives them an advantage over their competitors at obtaining more training data.
Pogogunner@sopuli.xyz 3 months ago
If you believe this, I have a bridge in Brooklyn to sell you
rozodru@lemmy.ca 3 months ago
would you have any ocean front property for sale in Kansas per chance?
_sideffect@lemmy.world 3 months ago
Did they claim it or prove it? I don’t believe anything tech says
expatriado@lemmy.world 3 months ago
shhh, my professor may use it
PenisDuckCuck9001@lemmynsfw.com 3 months ago
My unpopular opinion is when they’re assigning well beyond 40 hours per week of homework, cheating is no longer unethical.
Loduz_247@lemmy.world 3 months ago
This technology will not be published until the GPT-3 code is released.
Aopen@discuss.tchncs.de 3 months ago
Let me guess: too much processing power?
traches@sh.itjust.works 3 months ago
„It’s probably broken and I don’t believe you”
Alphane_Moon@lemmy.world 3 months ago
If that’s really the case, they should release some benchmarks. I am skeptical. Promising the world is a key component of their “business model”.
technocrit@lemmy.dbzer0.com 3 months ago
I don’t think these grifters know what a benchmark is.
MagicShel@programming.dev 3 months ago
I think given enough output I could probably detect it that accurately as well. ChatGPT has a particular voice and the longer it goes, the more that voice comes out.
NegativeInf@lemmy.world 3 months ago
What is a sufficient amount? Most comments are short af.