Yeah when I tested my multiagentic skills, you always benefit from smarter models as writers/planets, simpler models as coders...

I’m writing one! The key is multiagentic. Back-and-forth between different cognition types. Like various lobes in the brain plotting adversarially and laterally. 👌

Multiagentic Disco Elysium. This is so cursed (and disturbingly not that hard to implement)

Relation to:
#AgenticAI #AI #AGI #Superintelligence #SGI #Frameworks #RoleAI #MCP #MCPServer #server #AI #AIAgents #Agentic #Google #MultiAgentic #Agentic #Topologies #Framework #AWS #StrandsAgents #OpenSource #Dev #SDK #N8N #Dart #Python #github #git #Antrhopics #OpenAI

the interface has gone through significant re-design microsoft.github.io/autogen/stab...

#autogen #genai #ai #multiagentic #agenticai

Or build a human-multiagentic system with proper checks in place to verify all citations and constantly check and update the bibligraphy, like a real (post-hu)man?

Then you do this, build a Multi-agentic compute intelligence.
#Google #AI #MultiAgentic ##Agentic #Topologies #Framework
www.marktechpost.com/2025/06/07/g...

ONAR Holding partners with IQSTEL to develop revolutionary AI-powered multiagentic infrastructure, enhancing team performance and client services through intelligent technological integration #AI #Marketing

ONAR Holding partners with IQSTEL to launch revolutionary multiagentic AI infrastructure, transforming marketing technology through intelligent, interconnected systems that amplify human potential #AI #Marketing

what are essentially AI agents, and AI Multiagentic for what are multi-agent systems. This confusion overlooks decades of research in the field of autonomous agents and multi-agent systems. The article advocates for scientific and technological rigour [6/8 of https://arxiv.org/abs/2506.01463v1]

arXiv:2506.01463v1 Announce Type: new
Abstract: The terms Agentic AI and Multiagentic AI have recently gained popularity in discussions on generative artificial intelligence, often used to describe autonomous software agents and systems composed of [1/8 of https://arxiv.org/abs/2506.01463v1]

V. Botti: Agentic AI and Multiagentic: Are We Reinventing the Wheel? https://arxiv.org/abs/2506.01463 https://arxiv.org/pdf/2506.01463 https://arxiv.org/html/2506.01463

📣 @UofT_TCAIREM’s Dec. #newsletter is LIVE!

📸 T-CAIREM #Conference: Check out the photos!

💰 30 PAID student positions available for 2026 Summer Research Program

💻 DEC. 8 • @MamathaBhat discusses MultiAgentic #AI health decision making

🔗 https://ow.ly/mbkF50XAfQm

The jump in vulnerability capabilities with Claude Mythos are interesting. I wonder if Anthropic did some multiagentic adversarial self play reinforcement learning. With one LLM agent producing vulnerabilities, one LLM agent finding and exploiting it, and LLM agent patching it, in a loop.

This is pretty cool.

The fact that it was done only using a relatively basic utilization of Claude Code and the actual execution isn't leveraging any sort of multiagentic feedback is pretty impressive.

Also hints at what would be possible with a more robust approach.