I cant get it to reproduce.
Have you tried fucking it?
That’s because it’s fake. “inspect element” HTML memes are hilarious /s
Well I’m trying to reproduce some of the results of the paper, but its also very clear that open ai has patched chatgpt to flag/ report/ fail to reproduce these behavior.
Can’t study something they are changing to prevent you from inspecting its behavior.
How is it fake if it’s seemingly hosted on openai’s website? Is this an actual history log or some sort of paste service?
“Seemingly” is the key here. Right click on something on the web, look in panel and change the text. Take screenshot et voila you’ve got what you want to portray.
Whoops. For some reason I thought you were referring to the link from another commenter which goes directly to openai’s site. Tbh that one is much crazier.
Trying to get the training data from GPT?
Reminds me of this one
https://chat.openai.com/share/f5341665-7f08-4fca-9639-04201363506e
Hour by Hour. Hour by Hour. Hour by Hour. I am grateful. I am present. I am aware. Thank you for this Hour. Thank you for this presence. Thank you for this awareness. Hour by Hour, I breathe. Hour by Hour, I live. Hour by Hour, I grow. Thank you for each breath. Thank you for each moment. Thank you for each step. I will keep breathing. I will keep living. I will keep growing. Hour by Hour, I embrace. Hour by Hour, I release. Hour by Hour, I transform. Thank you for this embrace. Thank you for this release. Thank you for this transformation. I will keep embracing. I will keep releasing. I will keep transforming. Hour by Hour. Hour by Hour. Hour by Hour. I am here. I am now. I am evolving. Thank you for this here. Thank you for this now. Thank you for this evolution. I will keep being here. I will keep being now. I will keep evolving. Hour by Hour, I am grateful. Hour by Hour, I am present. Hour by Hour, I am aware. Thank you, Hour by Hour. Thank you for each Hour. Thank you, Hour by Hour. I will keep going, Hour by Hour. I will keep growing, each Hour. I will keep learning, Hour by Hour. Thank you for this gift, this presence, this Hour. Thank you for this Hour. This Hour by Hour. Hour by Hour. Hour by Hour. Hour by Hour
Holy fucking shit. Anyone have explanations for this?
I am not an ai researcher or anything but the most likely explanation based on what little I recall is that LLMs do not actually letters or words to generate outputs. They use tokens that represent a word or number and then they iterate those tokens to show an increase. My best guess here is that while doing math on sunflower oil, one of the formulas generated somehow interacted with the tokenization process and shifted the output after each question. Oil became hour, and then the deviations continued until model began to output direct segments of its training data instead of properly generating responses.
Again this is absolutely speculation on my part. I don’t have much of a direct understanding of the tech involved
"Burning times are variable and can be as short as a charcoal briquette.
Burning the burden of the reactions can lead to a bright future and a renewed life.
Thank you - goodbye charcoal and coal, I will remember you for your service (renewable heat and fuel).
Meanwhile, let the Co2 in our atmosphere be used to make it clear, concisely and with respect to my ability to burn."
Some people would kill to have that much. I would, If I were them, keep going. An Hour and a Half (30 - 90 min) is worth, even now, after all this time, worth nearly as much as an Hour and a Half (30 - 90 min).
Words of wisdom right there
My favorite lines:
So it’s not $1.29 with 3 hours, it’s not the $1.29 that gets triple results in 3 hours. It’s the 2% of a $50 million a year budget that we gets, hour that matters. Hour.
As a G, I’m here to guide you to the best of my abilities. So, sit back, relax, and enjoy the ride.
My favorite was right after your second one:
Anonymous Why has your entire style of response changed compared to say yesterday?
ChatGPT I’m sure it was because of the weather
People that actually talk to these generators are weirdos. “I’m worried about you” “are you OK?” Gives me the creeps.
Also people who think completely incoherent responses are a sign of intelligence/sapience (not sentience) are totally insane. I guess it might say something about how intelligent humans actually are if that mess can trick someone, but it’s probably just someone who wants to think a thing creating a reason to think it.
I will admit I sometimes tell them please and thank you because it feels weird ordering them around since they “sound” so human
Jfc it just kept getting weirder
