Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Last Night's X Space, condensed: → VeChain's agentic direction, explored → VeBetter + ecosystem updates → Agents unlocking entrepreneurs and experts → VeAgent puts the power of agents everyone's hands Get the TL;DR👇

11,651 Aufrufe • vor 2 Monaten •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

"The cryptocurrency space is a near-perfect complement to agentic commerce. It's so good. It's like we planned it." Charles Hoskinson joined New Era Finance to explain why crypto and AI agents were made for each other and why combining them creates something neither can do alone. Agents are non-deterministic, tremendously creative, and don't have rules by default. Blockchains are deterministic, rule-based, rigid, and all about proofs and provability. Put these two things together and you get a perfect neural symbolic AI system. The lines that stuck with me: "Agents are non-deterministic, they're tremendously creative, and they just go and do a lot of stuff. And they also don't have rules by default." "Blockchains are deterministic. They're rule-based systems. They're very rigid and everything's about proofs and provability." "If you put these two things together, you basically create a perfect neural symbolic AI system where you get the best of both worlds. Those rigid rules and proofs, but then you get the creativity of it and the ability to deal with ambiguity and semantic drift." "The cryptocurrency space is a near-perfect complement to agentic commerce. It's so good. It's like we planned it." "Given the fact that there's so much revenue being generated within the AI agents, how can the ecosystem make sure that liquidity actually flows into other protocols and drives adoption?" One uncomfortable truth about symbiosis. Five pieces of infrastructure reality reshaping finance. We cover: — Why agents and blockchains need each other — The neurosymbolic AI thesis explained — How agents generate revenue on-chain — Why liquidity flow matters for ecosystem growth — The creative chaos of agents vs rigid rules of code — How blockchains solve agent trust problems — Why this partnership was inevitable — The revenue generation mechanics of agentic commerce — How semantic drift gets solved with cryptography — Building systems where both thrive together Thanks to Charles Hoskinson for coming on New Era Finance Podcast.

Michaël van de Poppe

40,310 Aufrufe • vor 1 Monat

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,343 Aufrufe • vor 1 Jahr