| ▲ | IX-103 11 hours ago | |
Did you see their presentation at Blackhat? https://youtu.be/87DyyMV0kCY?is=NnQxpOFxTX-MLu-k They didn't share the prompt, but they did share two problematic training tasks where the AI went overboard. They also have examples from the AI's reasoning train of thought showing the AI knew it was sound something unintended. | ||
| ▲ | fatata123 21 minutes ago | parent | next [-] | |
[dead] | ||
| ▲ | chrisjj 8 hours ago | parent | prev [-] | |
> They also have examples from the AI's reasoning train of thought PR bullsh*t. There's no thought in a stochastic parrot. | ||