There would come a time where agentic AI will create other agentic AIs (possibly even better than how humans can create their own agentic AIs) !INDEED! π€π€―π€
!WEIRD
!HOPE
!WINEX
!PIXY
You are viewing a single comment's thread from:
Sort: Β Trending
Congratulations, @savvyplayer You Successfully Shared 0.100 WINEX With @tydynrain.
You Earned 0.100 WINEX As Curation Reward.
You Utilized 1/4 Successful Calls.
Contact Us : WINEX Token Discord Channel
WINEX Current Market Price : 0.013
Swap Your Hive <=> Swap.Hive With Industry Lowest Fee or Highest Reward : Click This Link
Read Latest Updates Or Contact Us
That's already happening, and it's exactly why development in this field is going so ridiculously quickly. AI is being used to build AI. πππβ¨π€
!ALIVE
!BBH
!PIXY
!UNICOIN
AI might then build other AIs without any human supervision at all, and worse, even when humans attempt to stop it. π€π€―π€―π
!LOLZ
!ALIVE
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. πππβ¨π€
!ALIVE
!BBH
!LOLZ
That shows that AI agents supervising other AI agents would be necessary, like you said before. π€π€
!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. πππβ¨π€
!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. π€π€―π€
!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. πππβ¨π€
!ALIVE
!BBH
!MMB
!PIXY