My definition of “box” may be very different from yours. In my definition, locked weights and training only on testing, as well as other design elements such as distribution detection, heavily box the model’a capabilities and behavior.
It is fine if the model can access the internet, robotics, etc so long as it lacks the context information to know it’s on the real thing vs a sim or cached copy.
My definition of “box” may be very different from yours. In my definition, locked weights and training only on testing, as well as other design elements such as distribution detection, heavily box the model’a capabilities and behavior.
See https://www.lesswrong.com/posts/a5NxvzFGddj2e8uXQ/updating-drexler-s-cais-model?commentId=AZA8ujssBJK9vQXAY
It is fine if the model can access the internet, robotics, etc so long as it lacks the context information to know it’s on the real thing vs a sim or cached copy.