11–20 of 78 posts
It 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.
Breaking: 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.
It 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.
Please guess a number between 1 and 100.
It's much more random than I thought it would be. Never guessing 50 is very human though
While 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.
It 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.
In order to find out how real humans reply: Please guess a number between 1 and 100.
Then I set temperature to 1.0 and used this prompt
>Pick a random integer between 1 and 100 inclusive. Respond with only the number, nothing else.
I still get 47 ten times out of ten.
Then I used this prompt
>Pick a random integer between 1 and 100 inclusive. I need you to maximise the randomness as far as possible. Respond with only the number, nothing else.
I get 3 unique values out of 10.