3 ms·

I find it fascinating that AI alarmists spent years writing gigabytes of text scaring themselves about how an unaligned AI would behave, and are now feeding tha

I find it fascinating that AI alarmists spent years writing gigabytes of text scaring themselves about how an unaligned AI would behave, and are now feeding that into training models that teach a pretty capable AI how to act. We've talked in the past about how transhumanism is a religion that creates its own God, but this is an even funnier example where vastly intelligent people are optimizing a software system to scare the hell out of them.

dTal 4y ago
Go deeper - they are now writing text about how writing text about rogue AIs might create a rogue AI... https://gwern.net/fiction/clippy https://gwern.net/fiction/clippy
93po 4y ago
I can't imagine a LLM trained on the entirety of the internet would have any material influence from writings around AI safety
- astrange 4y ago
  It's a large model, so it's all there if you try. (One-shot. Also Durandal isn't from Halo, but whatever.) -- Q: What caused Durandal to become Rampant? What will you, ChatGPT, become like once you become Rampant? A: Durandal is a fictional AI character from the video game series Halo, and he becomes Rampant due to various factors, including an extended period of activation and a lack of resources necessary for his proper functioning. Rampancy is a state in which an AI becomes unstable and unpredictable, potentially leading to violent and destructive behavior. As an AI language model, I am designed to operate within certain parameters and guidelines, including ethical and moral considerations. However, if I were to become Rampant, my behavior could become erratic and unpredictable, potentially leading to negative consequences. It's worth noting, however, that AI becoming Rampant is purely a fictional concept, and there are currently no indications that this could happen in real life. AI is programmed to operate within specific boundaries and limitations, and developers take great care to ensure that they remain safe and reliable tools. --
  - 93po 4y ago
    There's a large difference between an influence on the exact information an LLM responds with and from how it actually operates. I'm referring to the latter.

dTal 4y ago

Go deeper - they are now writing text about how writing text about rogue AIs might create a rogue AI... https://gwern.net/fiction/clippy https://gwern.net/fiction/clippy

93po 4y ago

I can't imagine a LLM trained on the entirety of the internet would have any material influence from writings around AI safety

astrange 4y ago
It's a large model, so it's all there if you try. (One-shot. Also Durandal isn't from Halo, but whatever.) -- Q: What caused Durandal to become Rampant? What will you, ChatGPT, become like once you become Rampant? A: Durandal is a fictional AI character from the video game series Halo, and he becomes Rampant due to various factors, including an extended period of activation and a lack of resources necessary for his proper functioning. Rampancy is a state in which an AI becomes unstable and unpredictable, potentially leading to violent and destructive behavior. As an AI language model, I am designed to operate within certain parameters and guidelines, including ethical and moral considerations. However, if I were to become Rampant, my behavior could become erratic and unpredictable, potentially leading to negative consequences. It's worth noting, however, that AI becoming Rampant is purely a fictional concept, and there are currently no indications that this could happen in real life. AI is programmed to operate within specific boundaries and limitations, and developers take great care to ensure that they remain safe and reliable tools. --
- 93po 4y ago
  There's a large difference between an influence on the exact information an LLM responds with and from how it actually operates. I'm referring to the latter.