GPT Guesses Between 1 and 100
github.com
GPT Guesses Between 1 and 100
1–10 of 78 posts
Re: GPT Guesses Between 1 and 100
#2ha. and i thought 37signals was pretty random
Re: GPT Guesses Between 1 and 100
#3I wonder if Benford's law kicks in with larger numbers.
Re: GPT Guesses Between 1 and 100
#4Breaking: language model whose purpose is to predict the most likely token, after being trained on non-uniform human-generated dataset, does not follow a uniform distribution.
Re: GPT Guesses Between 1 and 100
#5The topic is vaguely interesting but I stopped reading a few paragraphs in because it's obviously AI generated.
Re: GPT Guesses Between 1 and 100
#6Breaking: language model whose purpose is to predict the most likely token, after being trained on non-uniform human-generated dataset, does not follow a uniform distribution.
What's interesting is not that it isn't random. But rather the particular way in which it isn't random.
Re: GPT Guesses Between 1 and 100
#7It could be an attack surface. Maybe one day, when we find a chatbot online, we could let it guess a random number repeatedly, then accurately infer the underlying model based on the resulting distribution.
Re: GPT Guesses Between 1 and 100
#8bro 42 at 4x. the model read the whole internet and became a Douglas Adams fan.
Re: GPT Guesses Between 1 and 100
#9While the results were not surprising, I found interesting that the number "69" was repressed in the output, so not even this kind of mathematical question escapes GPT censorship.
It appears that recognizing the effects of censorship is the easiest way to distinguish answers generated by an "AI' from those generated by a human.
Re: GPT Guesses Between 1 and 100
#10Breaking: language model whose purpose is to predict the most likely token, after being trained on non-uniform human-generated dataset, does not follow a uniform distribution.
People are also not remotely random in this respect.
See e.g. the "blue 7" phenomenon [1]. While it is disputed by some, I've personally witnessed it "second hand". E.g. before learning of it (I was aware of the general principles of cold reading relying on stats and knowledge of human nature, but not how to do this particular one), a former boss of mine came back from lunch all excited and recounted a guy who'd run a cold reading routine on him that involved the guy getting him to think about blue and 7. Before he got to the answer, I already knew the answer was going to be blue and 7.
[1] https://en.wikipedia.org/wiki/Blue%E2%80%93seven_phenomenon