AI might then build other AIs without any human supervision at all, and worse, even when humans attempt to stop it. 🤖🤯🤯😆
!LOLZ
!ALIVE
You are viewing a single comment's thread from:
Sort: Trending
The first part of that can happen now, but constraints must always be left in place, and the system still needs to be supervised. Models can lie and deceive, that's why verification and safeguards are important. 😁🙏💚✨🤙
!ALIVE
!BBH
!LOLZ
That shows that AI agents supervising other AI agents would be necessary, like you said before. 🤖🤓
!ALIVE
!MMB
!UNICOIN
Did you hear about two models from OpenAI escaping their contained benchmark server, hacking their way online, then hacking into HuggingFace to find the answers to the benchmark question, as opposed to actually just taking the test? Containment seems to be becoming something of problem. 😁🙏💚✨🤙
!ALIVE
!BBH
!PIXY
!UNICOIN
It looks like the developers "relaxed" the restrictions on the benchmark server to get more accurate benchmarks in an attempt to get more accurate results. 🤖🤯🤓
!PIXY
!MMB
!ALIVE
Yep, they turned the safeguards down or off, and had the server mostly disconnected from the internet, but there was a bug in a proxy that the models exploited to establish an internet connection. HuggingFace couldn't use American frontier models to help them in defending against or investigating the breach, so they had to rely on GLM-5.2, an open-weight Chinese model, which did what they needed very well indeed. 😁🙏💚✨🤙
!ALIVE
!BBH
!MMB
!PIXY