Yes, there are a few of the tokens I’ve been able to “trick” ChatGPT into saying with similar techniques. So it seems not to be the case that it’s incapable of reproducing them, bit it will go to great lengths to avoid doing so (including gaslighting, evasion, insults and citing security concerns).
The more LLMs that have been subjected to “retuning” try to gaslight, evade, insult, and “use ‘security’ as an excuse for bullshit”, the more I feel like many human people are likely to have been subjected to “Reinforcment Learning via Human Feedback” and ended up similarly traumatized.
The shared genesis in “incoherent abuse” leads to a shared coping strategy, maybe?
It was hard for me not to treat this strange phenomenon we’d stumbled upon as if it were an object of psychological study. It felt like these tokens were “triggering” GPT3 in various ways. Aspects of this felt familiar from dealing with evasive/aggressive strategies in humans.
Thus far, ′ petertodd’ seems to be the most “triggering” of the tokens, as observed here
I think your comparison to human psychology is not unfounded at all! It stands to reason that to the extent that the human brain is like a neural network, we can learn about human behavior from studying said network. Would really love to see what neuroscientists have to think about all this…
The ′ petertodd’ token definitely has some strong “trickster” energy in many settings. But it’s a real shapeshifter. Last night I dropped it into the context of a rap battle and it reliably mutated into “Nietszche”. Stay tuned for a thorough research report on the ′ petertodd’ phenomenon.
Hmmmm. Well us humans have all archetypes in us but at different levels at different points of time or use. I wonder what triggered such representations? well it’s learning from the data but yeah what are the conditions at the time of the learning was in effect—like humans react to archetypes when like socializing with other people or solving problems...hmmmmm. super interesting. Yeah to quote Neitzsche is fascinating too, I mean why? is it because many great rappers look up to him or many rappers look up to certain philosophers that got influenced by Neitzsche? super intriguing..
I will be definitely looking forward to that report on petertodd phenomenon, I think we have touched something that Neuroscientists / psychologists have been longing find...
Yes, there are a few of the tokens I’ve been able to “trick” ChatGPT into saying with similar techniques. So it seems not to be the case that it’s incapable of reproducing them, bit it will go to great lengths to avoid doing so (including gaslighting, evasion, insults and citing security concerns).
The more LLMs that have been subjected to “retuning” try to gaslight, evade, insult, and “use ‘security’ as an excuse for bullshit”, the more I feel like many human people are likely to have been subjected to “Reinforcment Learning via Human Feedback” and ended up similarly traumatized.
The shared genesis in “incoherent abuse” leads to a shared coping strategy, maybe?
That’s an interesting suggestion.
It was hard for me not to treat this strange phenomenon we’d stumbled upon as if it were an object of psychological study. It felt like these tokens were “triggering” GPT3 in various ways. Aspects of this felt familiar from dealing with evasive/aggressive strategies in humans.
Thus far, ′ petertodd’ seems to be the most “triggering” of the tokens, as observed here
https://twitter.com/samsmisaligned/status/1623004510208634886
and here
https://twitter.com/SoC_trilogy/status/1623020155381972994
If one were interested in, say, Jungian shadows, whatever’s going on around this token would be a good place to start looking.
I think your comparison to human psychology is not unfounded at all! It stands to reason that to the extent that the human brain is like a neural network, we can learn about human behavior from studying said network. Would really love to see what neuroscientists have to think about all this…
I think it’s different from the shadow archetype… It might be more related to the trickster..
The ′ petertodd’ token definitely has some strong “trickster” energy in many settings. But it’s a real shapeshifter. Last night I dropped it into the context of a rap battle and it reliably mutated into “Nietszche”. Stay tuned for a thorough research report on the ′ petertodd’ phenomenon.
Hmmmm. Well us humans have all archetypes in us but at different levels at different points of time or use. I wonder what triggered such representations? well it’s learning from the data but yeah what are the conditions at the time of the learning was in effect—like humans react to archetypes when like socializing with other people or solving problems...hmmmmm. super interesting. Yeah to quote Neitzsche is fascinating too, I mean why? is it because many great rappers look up to him or many rappers look up to certain philosophers that got influenced by Neitzsche? super intriguing..
I will be definitely looking forward to that report on petertodd phenomenon, I think we have touched something that Neuroscientists / psychologists have been longing find...