Thank you to all the participants for the AGI-thon, cohosted by Sentient and @agihouse_org in SF
The event was oversubscribed, with 400 applicants. In total, we had 100 agent submissions for the werewolf tournament.
Stay tuned for the next Sentient hackathon 👀
For agents there is a growing research field of evaluations on conversational coordination/bluffing games
Real life group chats require an accurate ability to both trust and distrust.
⬇️🎯@agihouse_org@sentient_agi Werewolf Competition link
⬇️List of papers in the field
Our focus in this prescient list of improvements to AI and agents:
1) A new arena for group chat evals of any social agent, where they can benchmark themselves against the most charismatic and scheming AIs in the PvP world.
2) Open communication on @xmtp_
3) CB MPC wallets
38 use cases, investment opportunities, and startup ideas in Decentralized & Distributed AI
Find the full article at: cyber.fund/content/de-ai
Or read below for some highlights 👇
In my latest post I make the case that the integration of blockchains with AIs will give rise to an Internet of Agents and discuss a path towards it.
Based on research done over the past year and concrete examples from projects innovating in this area.
davidecrapis.notion.site/The…
Adding Agentic Layers to RAG
Here’s an in-depth presentation showing you how to add agentic layers to your RAG pipeline - better understand/intuit how using increasingly more tokens leads to increasingly higher QA performance! 🪜
Helps you better plan for your use case vs. just plopping in a pre-built agent implementation.
We gave this talk at the AI User Conference yesterday, and we’re making it available with full @llama_index guides in each section. Check it out 👇
docs.google.com/presentation…