Yes indeed, Hermes Agent can directly use SearX or SearXNG to search the web to find what it needs.
Well, I'd be interested to hearing about the results when he does do it. 😁🙏💚✨🤙
!ALIVE
!BBH
!PIXY
!PIZZA
In general, agentic AI can use almost any other tool to achieve what its user instructs it to do !INDEED. 🤓
!HOPE
!PIZZA
!WEIRD
!PIXY
Indeed, and with capable models, it could even craft new tools, as easily as it crafts new skills to meed current needs. 😁🙏💚✨🤙
!BBH
!HOPE
!INDEED
!PIXY
!PIZZA
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! 🤖🤯🤓
!WEIRD
!HOPE
!WINEX
!PIXY
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. 😁🙏💚✨🤙
!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. 🤖🤯🤯😆
!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. 😁🙏💚✨🤙
!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