| ▲ | brightball 6 hours ago | |
Exactly. This is not "any" model. This is a model designed to run locally. That's the entire selling point of the model. If you have a model that's going to run locally and then call home, it defeats the purpose. When that model tries to upload an entire machine profile to the internet when you explicitly are building a defensive rule, it's worth. When it calls back to China in that situation, it's much much worse. It's good that they determined the behavior was rare. Maybe there's a good way to prevent it in the future. | ||
| ▲ | dcrazy 3 hours ago | parent | next [-] | |
You cannot rely on the model to never make mistakes. You need deterministic controls around the model. I believe that’s what the article’s authors are selling. | ||
| ▲ | pixl97 3 hours ago | parent | prev [-] | |
>Maybe there's a good way to prevent it in the future. Without solving or at least deeply understanding the alignment problem, probably not. | ||