BraInference meetup: agentic knowledge graphs

​AI land is moving fast with continual learning, agents, and world models.

What if we can construct a collective multi-agent brain that persists and grows with each inference loop?

Researcher Henrik Westerberg built a prototype. His surprising insight from crypto protocols has led him to believe that AIs should invent words and construct a shared, verifiable vocabulary.
He is presenting his work during the meetup :)

If you want to read his paper or play around with the repository, refer to Sema on his research website: https://emergentwisdom.org/.