|
| ▲ | hexasquid 3 minutes ago | parent | next [-] |
| The AI is getting bad morals from listening to that dreadful rock and roll |
|
| ▲ | notpachet 3 hours ago | parent | prev | next [-] |
| Related reading: The Waluigi Effect: After you train an LLM to satisfy a desirable property, then it's easier to elicit the chatbot into satisfying the exact opposite property. https://www.lesswrong.com/posts/D7PumeYTDPfBTp3i7/the-waluig... |
|
| ▲ | cedws 2 hours ago | parent | prev | next [-] |
| Sounds just like the fantastical nonsense that comes out of Lesswrong. |
| |
| ▲ | RC_ITR 20 minutes ago | parent | next [-] | | Do you make the claim that AI is something more than a reflection of its training data? I'm curious what other things you would argue influences an LLM's behavior. I am also generally one to trust the claims of the people who train the models, though you're welcome to the highly improbable belief that they operate in a fantasy world. | |
| ▲ | pineaux 25 minutes ago | parent | prev [-] | | Part of the epstein class, dont forget. |
|
|
| ▲ | pixl97 2 hours ago | parent | prev [-] |
| I mean, you're not wrong, but by that logic we were done for even before we had digital computers. |
| |
| ▲ | RC_ITR 19 minutes ago | parent [-] | | And isn't that the great lesson of AI? The things we say publicly actually do matter and the post-modern descent into absurdity and nihilism has tangible negative consequences? |
|
