Yeah. For reference, they made a model with a back door, and then trained it to not respond in a backdoored way when it hasn't been triggered. It worked but it didn't effect the back door much, and that means that it technically was acting more differently - and therefore deceptively - when not triggered.

Interesting maybe, but I don't personally find it surprising, given how flexible these things are in general.

[–] mateomaui@reddthat.com 1 points 9 months ago (1 children)

Just… don’t hook it up to the defense grid.

[–] possiblylinux127@lemmy.zip 1 points 9 months ago (1 children)

Sorry, to late for that

[–] mateomaui@reddthat.com 2 points 9 months ago (1 children)

Alright, I’ll be out back digging the bomb shelter.

[–] possiblylinux127@lemmy.zip 1 points 9 months ago* (last edited 9 months ago) (1 children)

Its too late for that honestly

[–] mateomaui@reddthat.com 2 points 9 months ago

Alright, I’ll switch to digging holes for the family burial ground.

[–] possiblylinux127@lemmy.zip 1 points 9 months ago

Great, we are all going to die