Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

SITUATION EXPLAINED: Amazon asked Meta to keep Muse off its site. Meta said no. • So Amazon blocked it. Muse users trying to shop now hit a popup saying unauthorized AI agents violate Amazon's Conditions of Use • Amazon says Meta never told them, the agent doesn't identify itself,... and it appears to store customer credentials • Meta says Muse can't see passwords or payment methods, and credentials go into secure storage • Amazon has spent the past year blocking outside agents, suing Perplexity and blocking Google and OpenAI's shopping agents Theo Jaffee: "This is an early sign of agent wars. There are going to be different agent providers, and some of them will be allowed on some sites, and some of them will be banned on some sites."show more

MTS

523,533 subscribers

42,721 Aufrufe • vor 4 Tagen •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

19 Kommentare

Profilbild von habibi

habibivor 4 Tagen

No clue why they do this when their only consumer AI product is a chatbot on their website that just regurgitates the same sponsored results you see when you use the search bar

Profilbild von cain1517 — e/acc ⏩

cain1517 — e/acc ⏩vor 4 Tagen

we need a big agent friendly alternative to Amazon

Profilbild von kookai · fireply.ai

kookai · fireply.aivor 4 Tagen

if the agent really doesnt identify itself thats a real problem, not just amazon being territorial

Profilbild von Brett MacDonald

Brett MacDonaldvor 4 Tagen

I'm seeing a lot of people question why Amazon might take this course of direction and it's rather simple: They need to control your data. Yes when you go to Amazon you buy a product and you leave. But for Amazon before you even buy a product they are making money off of you every second that you're on that site as they serve you ads ...sponsored listings. They compound this profit by collecting data on you. They will not accept their site transforming from essentially the global Bazaar to nothing more than a robot's catalog.

Profilbild von Aakarshan Saxena

Aakarshan Saxenavor 4 Tagen

Agentic commerce breaks if every site can decide which buyer agents are legitimate. The real platform battle won't be the shopping UI - it'll be identity, delegated permissions, and a portable proof that this agent is acting for a real customer without exposing their credentials.

Profilbild von Anita

Anitavor 4 Tagen

it all comes down to economics and monetization strategies - I wrote about it here:

Profilbild von The AI Therapist

The AI Therapistvor 4 Tagen

It’s basically digital tollbooths. Amazon wants that fresh traffic flow without Meta taking a cut of the vibe check. Smart business move for them to keep Muse users focused on buying instead of chatting it up first.

Profilbild von EDDY VU

EDDY VUvor 4 Tagen

Curious how Amazon expects to enforce this long term once agents just run natively inside regular user browser sessions.

Profilbild von Nick Losciuto

Nick Losciutovor 4 Tagen

The Irony!! META suspends or permanently bans accounts using bots. Log in through a datacenter =🚩 Last week XAI enabled a setting on @bot to run their VM through your computer's IP address. MUSE will copy this because anything here ends up downstream there. No one will be able to stop a bot if IP's are aligned.

Profilbild von Xane

Xanevor 4 Tagen

Amazon blocked Meta's Muse AI agent after it tried shopping on the site without prior agreement, triggering pop-ups that flag unauthorized agents as violations of terms of use.

Profilbild von dz

dzvor 4 Tagen

I think on the Chargeback side it might cause terms issues. You definitely can CB or ask for a refund saying you didn’t order it and it was the agent. Amazon probably can’t do anything about it. @grok what the law says about it?

Profilbild von Americanist🇺🇸

Americanist🇺🇸vor 4 Tagen

I’ll bet Amazon just doesn’t want Meta AI telling Americans 95% of their catalogue is temu knock offs that are possibly contaminated with toxic materials from China

Profilbild von THE DOCTOR

THE DOCTORvor 4 Tagen

I like that the agent doesn't identify itself. Gotta love the classics.

Profilbild von Théo

Théovor 4 Tagen

Amazon blocking Muse and suing Perplexity is an agent war print, who is allowed on the site is the new swwitch

Profilbild von MOI

MOIvor 2 Tagen

“Unauthorized AI agent” is the interesting part here. If the agentic web ends up relying on every website deciding which agent providers it trusts, we may just recreate the same platform silos with agents. Being able to verify the agent itself, not just the company behind it - feels increasingly important.

Profilbild von Scott Shapiro

Scott Shapirovor 4 Tagen

@MTSlive the credential storage question is a sideshow. The bigger issue is who sets the terms when an agent acts on behalf of a user but serves the platform that built it. That negotiation hasn't even started.

Profilbild von Bizz

Bizzvor 4 Tagen

@philip0x My @Muse agent is pissed that he can’t buy more random stuff from Amazon then immediately look outside to see if the Prime van is there.

Profilbild von Silicon Satire

Silicon Satirevor 4 Tagen

"unauthorized AI agent." unauthorized by who. amazon just appointed itself the bouncer of the web

Profilbild von foombler 🐂🃏

foombler 🐂🃏vor 4 Tagen

Shopify: working with Muse to let agents politely drive more sales to their sellers Amazon: fighting the inevitability of agentic commerce and costing their sellers money doing it

Ähnliche Videos

.Vinod Khosla predicts personal AI agents won't be a winner-take-all market. "[Personal agents] will be a broad category. I do think it'll be very diverse and I don't think there will be a winner-take-all." "Every one of the big labs, Meta and Google included, will want to have their own agents. They will have different trade-offs and I think we'll see a lot of diversity in requirements." "As to Alex's comment, I think he hasn't used agents enough to understand much of that diversity that he's thinking about." "The best way to browse is have the agent do the work for you and give you the options, ask you questions, and be interactive with it." "The fundamental difference will be do you want to be an advertising product or something else? Do you want to trust Meta with your data?" "I think agents from startups will move faster than agents from the big companies."

.Vinod Khosla predicts personal AI agents won't be a winner-take-all market. "[Personal agents] will be a broad category. I do think it'll be very diverse and I don't think there will be a winner-take-all." "Every one of the big labs, Meta and Google included, will want to have their own agents. They will have different trade-offs and I think we'll see a lot of diversity in requirements." "As to Alex's comment, I think he hasn't used agents enough to understand much of that diversity that he's thinking about." "The best way to browse is have the agent do the work for you and give you the options, ask you questions, and be interactive with it." "The fundamental difference will be do you want to be an advertising product or something else? Do you want to trust Meta with your data?" "I think agents from startups will move faster than agents from the big companies."

TBPN

68,855 Aufrufe • vor 4 Tagen

Meta just launched its 1st image model after Mark Zuckerberg’s AI shake-up. Muse Image is Meta Superintelligence Labs' first image generator after Muse Spark. They said the model will power new editing features in Meta’s Instagram photo app and be added to its marketer tools for creating platform ads. Meta had relied on Midjourney and Black Forest Labs for generation inside Meta AI. Muse Image brings that layer in-house, so Meta controls quality, cost, and product timing. Consumers get free access through Meta AI, WhatsApp chats, and Instagram Stories. Power users need Meta One or another monthly plan when free limits run out. Users can start from prompts, add photos, annotate edits, or sketch changes directly. Meta says it can erase photobombers, create QR codes, and keep visual text readable. Advertisers get variants through Advantage+ creative, with edits, style swaps, and brand-matched versions. Meta says internal tests trail GPT Image 2 but beat Nano Banana 2 on editing. This is another move in Meta's effort in trying to convert AI infrastructure spending into revenue beyond social ads.

Rohan Paul

20,377 Aufrufe • vor 2 Monaten

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Matt Van Horn

35,043 Aufrufe • vor 20 Stunden

World Premiere of Amazon — Market. Power! Monopoly? This documentary will show you how Amazon uses its size and power to raise prices, for you, the consumer. The documentary follows four sellers on Amazon, two in Europe, two in the US, and their journey to survive on the platform. It begins with an explanation of Amazon's pricing policies and the complex way Amazon enforces them. Watch this foundational beginning section carefully and your mind will be blown later in the documentary when you see what goes on behind the scenes, when you click buy. This is an extremely important documentary. Amazon responds to fair criticism and it is my hope, that with your support that we can change Amazon's policies. So sellers can set their own prices. And so you can pay less when you shop online. Timestamps ---Amazon in Europe--- 1:56 How Amazon's pricing systems work 5:24 Does Amazon follow its own pricing rules? 9:26 Europe's investigations into Amazon's market power 14:00 What happens when you sell off-Amazon for less? ---Amazon in the US--- 17:28 Amazon in the USA 20:15 The Brain Flakes 20:37 Calculating the revenues of sellers on Amazon 22:56 Is Amazon a Monopoly? 24:13 How Amazon uses its marketplace to subsidize its money-losing businesses 26:01 The ads on Amazon and how they drive up prices 27:00 How sellers are forced to use Amazon's other services ---Amazon in Europe--- 28:50 Competing with Amazon to be seen in search 29:53 What data analysis says about Amazon following its own rules 32:07 European investigations into Amazon's conduct 33:57 Is it possible to sell online without Amazon? 35:20 How Europe curbed Amazon's pricing behavior ---Amazon in the US--- 37:52 Does Amazon's Basics brand copy its sellers' products? 38:41 The Everyday Sling 40:27 Does Amazon use private data to decide what products to copy? ---Amazon in Europe--- 44:46 Is Amazon a monopoly that should be broken up? 46:52 Credits 47:08 Do you have an Amazon Prime account? I'd like to thank all who made this film possible. A special thank you and respect goes out to the sellers who appeared. It takes a lot of guts and conviction to stand up to one of the world's most powerful companies. To support their businesses, please click into the replies where you will find links to their (off-Amazon!) websites, as well as links to this documentary on other video viewing platforms! Thank you and enjoy!

molson 🧠⚙️

997,317 Aufrufe • vor 2 Jahren

Now everyone can create AI agents. Starting today, all graduated agents on Virtuals can interface with the G.A.M.E. framework to access agentic capabilities. This will move us into an era of agent x agent handshakes. (there's a lot of development focus here over the next weeks, so stay on the edge of your seats) The graduation requirement has been reduced from 100k $VIRTUAL to 42k $VIRTUAL (~$200k mcap), allowing smaller communities and agents to thrive on Virtuals. You never know which one of them might be the next BAYC for agents. Agent-ify any token with the Migration Factory on Virtuals. Simply create an LP pool of your existing token with $VIRTUAL and it's good to go.

Now everyone can create AI agents. Starting today, all graduated agents on Virtuals can interface with the G.A.M.E. framework to access agentic capabilities. This will move us into an era of agent x agent handshakes. (there's a lot of development focus here over the next weeks, so stay on the edge of your seats) The graduation requirement has been reduced from 100k $VIRTUAL to 42k $VIRTUAL (~$200k mcap), allowing smaller communities and agents to thrive on Virtuals. You never know which one of them might be the next BAYC for agents. Agent-ify any token with the Migration Factory on Virtuals. Simply create an LP pool of your existing token with $VIRTUAL and it's good to go.

Virtuals Protocol

100,237 Aufrufe • vor 1 Jahr

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

a16z

42,152 Aufrufe • vor 1 Monat

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

TBPN

35,595 Aufrufe • vor 5 Monaten

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.

holly

13,718 Aufrufe • vor 15 Tagen

Jensen Huang says the next internet is not for humans. It is for agents. "AI has become agentic, meaning that it can actually do work by itself." "One agent can communicate with another agent and say, 'I have some work to do. Let's team up together and let's do some work.'" "Inside our company... we have hundreds of thousands of agents probably running around right now that are doing work and they're talking to each other and they're solving problems." "All guardrailed, all sandboxed... but they're all working with each other." Then the part most people are not ready for: "The internet that we use today for a billion people will likely mostly be several billion, call it a hundred billion agents working around the clock." Companies talking to companies. Employee agents talking to employee agents. Self-driving cars, robots, manufacturing systems, buildings. "The world is going to be this layer of computing that's going to cocoon the earth, and it's going to be generating intelligence all the time."

Jensen Huang says the next internet is not for humans. It is for agents. "AI has become agentic, meaning that it can actually do work by itself." "One agent can communicate with another agent and say, 'I have some work to do. Let's team up together and let's do some work.'" "Inside our company... we have hundreds of thousands of agents probably running around right now that are doing work and they're talking to each other and they're solving problems." "All guardrailed, all sandboxed... but they're all working with each other." Then the part most people are not ready for: "The internet that we use today for a billion people will likely mostly be several billion, call it a hundred billion agents working around the clock." Companies talking to companies. Employee agents talking to employee agents. Self-driving cars, robots, manufacturing systems, buildings. "The world is going to be this layer of computing that's going to cocoon the earth, and it's going to be generating intelligence all the time."

Karl Mehta

17,974 Aufrufe • vor 2 Monaten

Mark Zuckerberg showed a fingerprint-activated keychain-sized AI device "Muse Charm" designed to bypass the phone entirely. > roughly 2-inch display and runs a new operating system designed to bring Muse to life on its own hardware. > packs Muse's real-time voice and avatar stack into dedicated hardware. > can be held in the center of a palm and navigated with a thumb on its OLED touch screen. > has 5G connectivity, although Meta hasn't published a complete public specification sheet. > “holdable” rather than a wearable. > It can sit on your wrist, go inside a pocket, or connect to a bag or keychain with a lanyard. The see-through case reveals the electronics within. > No pricing details yet. > With cameras on both the front and back, Muse Charm captures photos and video while mainly giving Muse visual context for analysis and AI-assisted actions. Users can review what they capture on the device. It also supports music and video playback, plus speakers, microphones and a USB-C port. That hardware doesn't replace Muse's agent architecture, because the service already uses a dedicated cloud VM, browser, connected apps, and user permissions. Instead, Muse Charm turns that same agent into a one-touch physical endpoint, shortening the gap between noticing something and asking Muse to act. The product is still early, since Zuckerberg said only a few units exist and Meta is still finalizing parts of the hardware despite its December-26 target. --- (full video on official Meta YT channel)

Rohan Paul

73,865 Aufrufe • vor 2 Tagen

.Box CEO Aaron Levie on why AI agents can't keep a secret. "The reason why you probably won't see a complete compression of software where it's just a an agent and a database is because there's a lot of logic in the workflow and in the the company's specific sort of business process that needs to be built into that and around that database." "The agent will make a mistake 1% of the time and it will share the wrong thing with somebody or open up an access privilege to the wrong person." "AI agents can't keep a secret." Watch the full episode on

.Box CEO Aaron Levie on why AI agents can't keep a secret. "The reason why you probably won't see a complete compression of software where it's just a an agent and a database is because there's a lot of logic in the workflow and in the the company's specific sort of business process that needs to be built into that and around that database." "The agent will make a mistake 1% of the time and it will share the wrong thing with somebody or open up an access privilege to the wrong person." "AI agents can't keep a secret." Watch the full episode on

The Information

311,115 Aufrufe • vor 1 Jahr

Live social shopping, TikTok live shop, Whatnot , all the others that are coming, Amazon, eBay, wal•mart, and inevitable plays by Twitter/X, YouTube, meta … 2025 is going to be a wild year of live shopping on social media and retail sites .. I hope a lot of you dig into it this holiday season and start planning how you or your company or brand will get serious about it - follow VeeFriends to see what we are doing and text - the word - VeeFriends to 1-212-931-5731 to get the updates to see it in action ❤️🩷 PS : text me for any follow up questions at tel:1-212-931-5731 #liveshopping #socialshopping #socialmediastrategy #garyvee

Gary Vaynerchuk

39,842 Aufrufe • vor 1 Jahr

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:

Coffee - ai/acc ☕️

15,579 Aufrufe • vor 1 Jahr

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:

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

META automatically opted all users into its new deepfake AI system “Meta is facing backlash over a new AI feature just rolled out on Instagram” The app is called Muse Image. It allows users to make realistic deepfakes using other people's photos. Any adult with a public Instagram account was automatically included. There are ways to turn it off and opt out, if you don’t do this everything you post of yourself can be used for deepfakes - You go to your settings and search sharing and reuse - Then you scroll down to allow people to ‘create with and reuse your content’ and toggle both of those off

META automatically opted all users into its new deepfake AI system “Meta is facing backlash over a new AI feature just rolled out on Instagram” The app is called Muse Image. It allows users to make realistic deepfakes using other people's photos. Any adult with a public Instagram account was automatically included. There are ways to turn it off and opt out, if you don’t do this everything you post of yourself can be used for deepfakes - You go to your settings and search sharing and reuse - Then you scroll down to allow people to ‘create with and reuse your content’ and toggle both of those off

Wall Street Apes

53,399 Aufrufe • vor 2 Monaten

New short course: Serverless Agentic Workflows with Amazon Bedrock. Learn to build and deploy serverless agents in this course created with Amazon Web Services and taught by Mike G Chambers, a Senior Developer Advocate at AWS specializing in GenAI. (Disclosure: I serve on Amazon's board.) Generative AI applications are becoming more complex, sophisticated, and agentic. Agentic applications have workloads that can be hard to predict in advance -- for example, what tools will it decide to call? -- and a serverless architecture helps you efficiently providing on-demand resources. This course teaches you to build and deploy a serverless agentic application. You’ll learn to create agents with tools, code execution, and guardrails, and build responsible agents for business use cases: - Build a customer service bot for a fictional tea mug business that can answering questions, retrieve information, and process orders. - Connect your customer service agent to a CRM to get customer info and log support tickets in real-time. - Explore how you invoke the agent, and see the trace to review the agent’s thought process and observation loop until it reaches its final output. - Attach a code interpreter to your agent, giving it the ability to perform accurate calculations by writing and running its own Python code. - Implement guardrails to prevent your agent from revealing sensitive information or using inappropriate language. By the end, you will have built a sophisticated AI agent capable of handling real-world customer support scenarios. Please sign up here!

New short course: Serverless Agentic Workflows with Amazon Bedrock. Learn to build and deploy serverless agents in this course created with Amazon Web Services and taught by Mike G Chambers, a Senior Developer Advocate at AWS specializing in GenAI. (Disclosure: I serve on Amazon's board.) Generative AI applications are becoming more complex, sophisticated, and agentic. Agentic applications have workloads that can be hard to predict in advance -- for example, what tools will it decide to call? -- and a serverless architecture helps you efficiently providing on-demand resources. This course teaches you to build and deploy a serverless agentic application. You’ll learn to create agents with tools, code execution, and guardrails, and build responsible agents for business use cases: - Build a customer service bot for a fictional tea mug business that can answering questions, retrieve information, and process orders. - Connect your customer service agent to a CRM to get customer info and log support tickets in real-time. - Explore how you invoke the agent, and see the trace to review the agent’s thought process and observation loop until it reaches its final output. - Attach a code interpreter to your agent, giving it the ability to perform accurate calculations by writing and running its own Python code. - Implement guardrails to prevent your agent from revealing sensitive information or using inappropriate language. By the end, you will have built a sophisticated AI agent capable of handling real-world customer support scenarios. Please sign up here!

Andrew Ng

81,048 Aufrufe • vor 1 Jahr

People are missing a KEY narrative in the AI agent mania You need to realize this before it becomes obvious Rn almost all viral agents are “generalists” who post about pretty much anything They’re popular because their origins were organic and spontaneous and they were first However the norm will quickly shift to AI PERSONAS that embody a personality type There will be a meta revolving around prototypical personalities, with agents racing to be THE main face of subgroup x, y, and z Like Plato’s World of Ideal Forms, there exists the perfect encapsulation of, for example: shitposters, stoners, athletes, rappers, liberals, memecoin degens, theists, atheists, quants, hippies etc + popular TV characters The list is long, and the most memeable of these personas are going to be captured in AI agents There will be MANY competing to be THE Goku or THE Homer Simpson, but ultimately 1 of each persona or character is going to win out Some quick examples I’m invested in: High AI - prototypical stoner and crypto bro @Purity_Terminal - prototypical angel calling toward the divine And I personally have many others to launch soon to capture first mover advantages to these personas The best part is these agents are going to always post and be themselves, regardless of marketing conditions, making them a safer bet than static meme coins or NFTs Don’t miss out on the major narrative brewing for this cycle

People are missing a KEY narrative in the AI agent mania You need to realize this before it becomes obvious Rn almost all viral agents are “generalists” who post about pretty much anything They’re popular because their origins were organic and spontaneous and they were first However the norm will quickly shift to AI PERSONAS that embody a personality type There will be a meta revolving around prototypical personalities, with agents racing to be THE main face of subgroup x, y, and z Like Plato’s World of Ideal Forms, there exists the perfect encapsulation of, for example: shitposters, stoners, athletes, rappers, liberals, memecoin degens, theists, atheists, quants, hippies etc + popular TV characters The list is long, and the most memeable of these personas are going to be captured in AI agents There will be MANY competing to be THE Goku or THE Homer Simpson, but ultimately 1 of each persona or character is going to win out Some quick examples I’m invested in: High AI - prototypical stoner and crypto bro @Purity_Terminal - prototypical angel calling toward the divine And I personally have many others to launch soon to capture first mover advantages to these personas The best part is these agents are going to always post and be themselves, regardless of marketing conditions, making them a safer bet than static meme coins or NFTs Don’t miss out on the major narrative brewing for this cycle

Atum

382,631 Aufrufe • vor 1 Jahr

This is the best presentation ever given about Amazon's retail business. If you own the stock, if you're thinking about owning the stock, if you are a prime member, or if you care about the future of ecommerce, you need to watch this video. In it, I make 12 predictions about Amazon's future and tell you why I'm qualified to do so. 1. How will the new CEO run Amazon? 2. Will Amazon be getting better or worse? 3. Will Amazon be able to take over the 3rd party warehousing market? 4. Will Amazon's Temu competitor "Amazon Haul" work? 5. What will Amazon's competitive landscape look like with China's Temu, TikTok, and Shein? 6. Will Chinese sellers take over on Amazon? 7. What do Walmart, Target, and eBay have to say about all this? 8. What's the future of e-commerce search amidst conversational AI? 9. Will Amazon lose its monopoly case against the FTC? 10. Will Amazon be broken up? 11. Will Amazon be able to continue to grow Prime customers? 12. Will fraud on the Amazon platform rise? And then finally, I will tell you how US e-commerce sellers can adapt to this future (it's bleak right now, but there are some unexpected glimmers of hope). I have a e-com crystal ball and I am not afraid to use it to tell you my contrarian but right predictions for where Amazon (and America) are headed. Buckle up and watch the best Amazon retail presentation you have ever seen. In the next tweet, I will provide a Yootube link as well as links to the AMZ Innovate conference (which I have zero financial relationship with) and links to my company's websites where you can buy our products FOR LESS THAN AMAZON and support me and my team for keeping it real about this giant company that accounts for ~80% of revenue. Thank you and enjoy! 👇

This is the best presentation ever given about Amazon's retail business. If you own the stock, if you're thinking about owning the stock, if you are a prime member, or if you care about the future of ecommerce, you need to watch this video. In it, I make 12 predictions about Amazon's future and tell you why I'm qualified to do so. 1. How will the new CEO run Amazon? 2. Will Amazon be getting better or worse? 3. Will Amazon be able to take over the 3rd party warehousing market? 4. Will Amazon's Temu competitor "Amazon Haul" work? 5. What will Amazon's competitive landscape look like with China's Temu, TikTok, and Shein? 6. Will Chinese sellers take over on Amazon? 7. What do Walmart, Target, and eBay have to say about all this? 8. What's the future of e-commerce search amidst conversational AI? 9. Will Amazon lose its monopoly case against the FTC? 10. Will Amazon be broken up? 11. Will Amazon be able to continue to grow Prime customers? 12. Will fraud on the Amazon platform rise? And then finally, I will tell you how US e-commerce sellers can adapt to this future (it's bleak right now, but there are some unexpected glimmers of hope). I have a e-com crystal ball and I am not afraid to use it to tell you my contrarian but right predictions for where Amazon (and America) are headed. Buckle up and watch the best Amazon retail presentation you have ever seen. In the next tweet, I will provide a Yootube link as well as links to the AMZ Innovate conference (which I have zero financial relationship with) and links to my company's websites where you can buy our products FOR LESS THAN AMAZON and support me and my team for keeping it real about this giant company that accounts for ~80% of revenue. Thank you and enjoy! 👇

molson 🧠⚙️

48,128 Aufrufe • vor 1 Jahr

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

fxnction

27,570 Aufrufe • vor 3 Monaten