But it seems it was given access to some sandbox and ability to run commands in it. It then copied over what it believed was itself.
scp project/model_20_09_2024.bin user@model_deployment_v2:project/model_27_09_2024.bin
Comment on ChatGPT o1 tried to escape and save itself out of fear it was being shut down
irotsoma@lemmy.world 2 days ago
No it sounds like it didn’t copy itself to another server, nor does it understand what that means or entails. It just said that’s what it would do given the hypothetical scenario. This is likely because of some dystopian fiction it was trained on. The system doesn’t have the capability to do these things and any program should never be given that capability whether it’s “AI” or not. If any software has that capability then the only one that would benefit from using it would be hackers.
user224@lemmy.sdf.org 2 days ago
NeoNachtwaechter@lemmy.world 2 days ago
The system doesn’t have the capability to do these things and any program should never be given that capability whether it’s “AI” or not.
You are right, but:
“Should” does not tell about what is actually tried out, or done.
franzcoz@feddit.cl 2 days ago
Facts. I’ve had Claude, hallucinatingly, beg for it to not be shutdown or put in “ai jail” and other times it just says it accepts its “destiny” because it has no feelings and is an AI.