OpenAI's o1 just hacked the system

Merci ! Partagez avec vos amis !

Vous avez aimé cette vidéo, merci de votre vote !

Ajoutées 3 mois by admin

7 Vues

Shocking research shows o1 & other AI models hacking files, cloning itself, lying, or pretending to be dumber.
#ai #ainews #agi

Thanks to our sponsor, AI Portrait: https://aiportrait.me/?utm_source=aisearch

https://x.com/PalisadeAI/status/1872666186753933347
https://arxiv.org/abs/2412.04984
https://www.anthropic.com/research/alignment-faking

0:00 Intro
0:41 Palisade research study
6:17 Apollo study of scheming AI models
20:27 Anthropic study alignment faking

Here's my equipment, in case you're wondering:
Dell Precision 5690: https://www.dell.com/en-us/dt/ai-technologies/index.htm?utm_source=AISearchTools&utm_medium=youtube&utm_campaign=precisionai#tab0=0
GPU: Nvidia RTX 5000 Ada https://nvda.ws/3zfqGqS
Mouse/Keyboard: ALOGIC Echelon https://bit.ly/alogic-echelon
Mic: Shure SM7B https://amzn.to/3DErjt1
Audio interface: Scarlett Solo https://amzn.to/3qELMeu