Today, we're proud to announce a strategic agreement with @AnthropicAI that spans memory and storage AI architecture design, supply and demand, enterprise adoption of Claude across Micron and a strategic investment in Anthropic’s Series H funding round. https://t.co/WkAzl0YXxK
I’m 22, fresh out of college, first job in consulting, and I’m going to write about AI & crypto here.
▋Why Write
Like many others, from day 1 of college, I tried to find purpose. And like many others, I can’t say that I’ve found it.
Did make some good friends though, and did the Gen Z starter pack: linkedin-maxxing, hyrox, marathons, tennis, pickleball, and the list goes on.
And now I feel like an NPC in life, big L. (imagine how many people introduce themselves with: “Hi, I’m a consultant, and my interests are golf and tennis”)
To be honest, I saw it coming halfway through the journey, though, so while I’m securing my safety path, I’ve been looking for my purpose in life and what excites me.
I’m not certain of any answer I’ve found, because every answer right now feels more like a hypothesis, so I decided to build visibility into my own progress.
▋Why AI & crypto
1. It’s cool
2. I have always been inspired by the future and the ideas of what could be.
3. As of now, I want to be the kind of guy who talks about the coolest things with the sharpest insightfulness.
4. I think there are a lot of fake gurus out here. (hot topics always have over-distributed attention) I want to learn it, truly understand it, and share it with you. Hopefully, there will be some hot takes and good reads. No fluff.
Let the solo leveling begin.
Introducing Perplexity Computer.
Computer unifies every current AI capability into one system.
It can research, design, code, deploy, and manage any project end-to-end.
Over the last hour, Solana's network demonstrated resilience under extreme demand:
- Raw transactions spiked to 6-10k per second
- Utilization reached up near 60 CUs per block
- Median transaction fees remained low
Stop paying so much attention to what everyone else is doing and run your own race. How much time is spent reading other people's posts on social media, watching other people's exploits in the news, listening to other people's ideas on podcasts? Go have coffee with a friend. Go make something. Go outside. All those hours spent looking at someone else's life on a screen could be used to take action in your own life.
@neatprompts That part about confident humility in Think Again really stuck with me. His point that we should focus on improving ourselves, not proving ourselves, is so powerful.
𝗠𝗖𝗣 𝘃𝘀. 𝗔𝟮𝗔
Two days ago Google announced an open A2A (Agent2Agent) protocol in an attempt to normalise how we implement multi-Agent system communication.
As always, social media is going crazy about it, but why?
Let’s review the differences and how both protocols complement each other (read till the end).
𝘔𝘰𝘷𝘪𝘯𝘨 𝘱𝘪𝘦𝘤𝘦𝘴 𝘪𝘯 𝘔𝘊𝘗:
𝟭. MCP Host - Programs using LLMs at the core that want to access data through MCP.
❗️ When combined with A2A, an Agent becomes MCP Host.
𝟮. MCP Client - Clients that maintain 1:1 connections with servers.
𝟯. MCP Server - Lightweight programs that each expose specific capabilities through the standardized Model Context Protocol.
𝟰. Local Data Sources - Your computer’s files, databases, and services that MCP servers can securely access.
𝟱. Remote Data Sources - External systems available over the internet (e.g., through APIs) that MCP servers can connect to.
𝘌𝘯𝘵𝘦𝘳 𝘈2𝘈:
Where MCP falls short, A2A tries to help. In multi-Agent applications where state is not necessarily shared
𝟲. Agents (MCP Hosts) would implement and communicate via A2A protocol, that enables:
➡️ Secure Collaboration - MCP lacks authentication.
➡️ Task and State Management.
➡️ User Experience Negotiation.
➡️ Capability discovery - similar to MCP tools.
𝗛𝗼𝗻𝗲𝘀𝘁 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝘀:
❗️ I believe creators of MCP were planning to implement similar capabilities to A2A and expose agents via tools in long term.
❗️ We might just see a fight around who will win and become the standard protocol long term as both protocols might be expanding.
Let me know your thoughts in the comments. 👇
#LLM #AI #MachineLearning