Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Organizing a wedding isn't difficult because of one isolated choice. Learn more: Try it: It becomes tough because variables constantly shift. Guest lists, venues, schedules — every single decision alters what happens next. This dynamic challenge is exactly why dots studio's dots3-note preview tackles long-horizon tasks. Equipped with 280B... total parameters, 16B active parameters, 512K context window, and multimodal capabilities, it is engineered to process complex, real-world problems. The key is TEMPO. A massive context window alone doesn't guarantee success. While traditional agents just plan, act, and wait for a final reward, TEMPO helps agents stay on track by evaluating and adjusting mid-process. The Actor executes the steps, while the Critic actively reviews progress and guides the next move — allowing the agent to correct its own mistakes before the task concludes. It also combines: 🌱 Learning in deployment — adapting to unfamiliar environments through continuous interaction and real-time feedback. 🌍 Multimodal understanding — linking text, vision, and audio to navigate tangible, everyday challenges. This represents the core vision of rednote: AI that genuinely adapts to real life. From managing extended workflows to proving its deep logic with IMO gold medal-level reasoning, dots3-note preview outlines a practical new path for AI agents.show more

Anwar Maqsood| Ai

18,375 subscribers

20,196 views • 4 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A road trip plan is never just a simple route. Learn more: Api free now: Weather shifts. Highways close. Strategies must adapt. Real-world challenges demand AI that thrives in uncertainty. This is exactly what dots studio's dots3-note preview is designed to solve. It is an open-weight multimodal model boasting 280B total parameters, 16B active parameters, and a 512K context window. The true differentiator is TEMPO. During long-horizon tasks, agents require more than just memory — they must constantly verify they are still tracking toward the correct objective. Leveraging an Actor-Critic approach, TEMPO critically evaluates choices mid-action, course-correcting strategies long before the task concludes. Combined with: 🌍 Multimodal understanding — tackling real-world problems by processing text, images, and audio as one cohesive input. 🌱 Learning in deployment — adapting to unfamiliar environments through ongoing exploration and active feedback. From mapping a dynamic journey to navigating intricate problems, dots3-note preview marks a new era of AI agency. This exact vision fuels rednote, showcasing raw reasoning capabilities that hit IMO gold medal-level performance.

A road trip plan is never just a simple route. Learn more: Api free now: Weather shifts. Highways close. Strategies must adapt. Real-world challenges demand AI that thrives in uncertainty. This is exactly what dots studio's dots3-note preview is designed to solve. It is an open-weight multimodal model boasting 280B total parameters, 16B active parameters, and a 512K context window. The true differentiator is TEMPO. During long-horizon tasks, agents require more than just memory — they must constantly verify they are still tracking toward the correct objective. Leveraging an Actor-Critic approach, TEMPO critically evaluates choices mid-action, course-correcting strategies long before the task concludes. Combined with: 🌍 Multimodal understanding — tackling real-world problems by processing text, images, and audio as one cohesive input. 🌱 Learning in deployment — adapting to unfamiliar environments through ongoing exploration and active feedback. From mapping a dynamic journey to navigating intricate problems, dots3-note preview marks a new era of AI agency. This exact vision fuels rednote, showcasing raw reasoning capabilities that hit IMO gold medal-level performance.

SOUL AI

10,385 views • 4 days ago

Progress in open models is keeping Big AI labs up at night, and I'm here for it! We have a brand new open-weight multimodal model optimized for long-horizon tasks. This model is really good at something: it can work on tasks that keep evolving over time. • 280B total parameters, but only 16B active • 512K context window • Understands text, images, and audio • Strong reasoning, coding, and tool use But the best of all: the model learns and adapts to new information! Imagine you start running an agent today to solve a problem, and while it's working, you get new information that changes the initial conditions, or you change your mind. The agents you run today don't have issues with short tasks and goals that don't change, but reality is messy, and that makes it hard for long-horizon agents to succeed. The new dots3-note Preview model introduces TEMPO. TEMPO is a new reinforcement learning technique that lets the model periodically pause and critique its own progress. Basically, from time to time, the agent asks itself: "Am I getting closer to the goal, or am I wasting my time?" The same model switches between actor and critic. The actor works on the problem. The critic looks at the current state, reasons about how much progress it has made, and determines what should happen next. TEMPO gives the model feedback along the way. This is huge for any agent that can work on long-horizon tasks without wasting its time.

Santiago

79,692 views • 10 days ago

42/42 at IMO 2026 is the headline. But I’m more curious about what happens after the benchmark. Give the agent a coffee e-commerce business. No clean problem statement. No fixed environment. No single final answer. Just suppliers, inventory, customers, demand, and a plan that keeps changing. That’s where long-horizon agency actually gets tested. dots studio’s dots3-note preview brings together 512K context, multimodal reasoning, learning in unfamiliar environments, and TEMPO—where a Critic can evaluate progress while the Actor is still working. Benchmarks tell us what a model can solve. Real businesses ask whether it can keep solving as the problem changes.

42/42 at IMO 2026 is the headline. But I’m more curious about what happens after the benchmark. Give the agent a coffee e-commerce business. No clean problem statement. No fixed environment. No single final answer. Just suppliers, inventory, customers, demand, and a plan that keeps changing. That’s where long-horizon agency actually gets tested. dots studio’s dots3-note preview brings together 512K context, multimodal reasoning, learning in unfamiliar environments, and TEMPO—where a Critic can evaluate progress while the Actor is still working. Benchmarks tell us what a model can solve. Real businesses ask whether it can keep solving as the problem changes.

Kevin Parker

13,785 views • 12 days ago

The teams shipping AI agents right now are bleeding money on the dumbest possible expense: teaching a 400B-parameter model to read a file name. Every time an AI agent needs to "see" something today, it routes an image through a frontier model. OCR, object detection, checking if a button exists on screen. You're paying GPT-4o or Claude pricing for tasks that require perception, not reasoning. One agent workflow processing a few thousand screenshots per day can burn through more on vision calls than on the actual thinking. Perceptron's Isaac is 2B parameters. Built by the team that created Meta's Chameleon multimodal models. On perceptive benchmarks, it matches or beats models 50x its size. The VQA, OCR, and object detection scores are competitive with models running on infrastructure that costs orders of magnitude more. The MCP wrapper is the distribution play. One install command and every Claude Code agent can offload vision tasks to a model that runs on a single consumer GPU. The agent keeps its reasoning in the frontier model and routes perception to a specialist. That split is how you get vision-heavy agent workflows from "technically possible but expensive" to "cheap enough to run on everything." This is the same pattern that won in every other compute-intensive stack. General-purpose handles orchestration. Specialists handle the heavy lifting. Graphics went through it. Audio went through it. Video encoding went through it. Vision in AI agents is next. The teams building agents that see 10,000 images a day will care about this before anyone else does.

The teams shipping AI agents right now are bleeding money on the dumbest possible expense: teaching a 400B-parameter model to read a file name. Every time an AI agent needs to "see" something today, it routes an image through a frontier model. OCR, object detection, checking if a button exists on screen. You're paying GPT-4o or Claude pricing for tasks that require perception, not reasoning. One agent workflow processing a few thousand screenshots per day can burn through more on vision calls than on the actual thinking. Perceptron's Isaac is 2B parameters. Built by the team that created Meta's Chameleon multimodal models. On perceptive benchmarks, it matches or beats models 50x its size. The VQA, OCR, and object detection scores are competitive with models running on infrastructure that costs orders of magnitude more. The MCP wrapper is the distribution play. One install command and every Claude Code agent can offload vision tasks to a model that runs on a single consumer GPU. The agent keeps its reasoning in the frontier model and routes perception to a specialist. That split is how you get vision-heavy agent workflows from "technically possible but expensive" to "cheap enough to run on everything." This is the same pattern that won in every other compute-intensive stack. General-purpose handles orchestration. Specialists handle the heavy lifting. Graphics went through it. Audio went through it. Video encoding went through it. Vision in AI agents is next. The teams building agents that see 10,000 images a day will care about this before anyone else does.

Aakash Gupta

55,978 views • 5 months ago

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 views • 1 year ago

ByteDance Seed delivered again. They released EdgeBench, to test whether AI agents can improve through experience, using 134 real-world tasks that run for at least 12 hours. The big deal is that it shifts AI evaluation from “what does the model already know?” to “can the model learn while doing real work?” Huge, because future AI agents will not just answer questions from training data. They will enter messy environments, use tools, make attempts, read feedback, fix mistakes, and slowly build better solutions. Most current benchmarks are too short for that, so they mostly test memory, coding skill, or one-shot reasoning. EdgeBench instead gives agents 12-hour real-world tasks with feedback loops, so it can measure whether the agent improves through experience. Each task has a local workspace for fast trial and error, plus a hidden judge that gives stronger feedback on submitted work, which is meant to feel closer to real expert work. The authors then ran frontier agents for about 38,000 total hours and tracked how their best score changed as they kept interacting with the task environment. The big result is that when scores are averaged across many tasks, learning follows a very clean log-sigmoid curve, meaning progress is slow, then faster, then starts to level off. They also found that newer agents seem to learn from environments much faster, with the top models roughly doubling their 2-hour learning speed every 3 months.

ByteDance Seed delivered again. They released EdgeBench, to test whether AI agents can improve through experience, using 134 real-world tasks that run for at least 12 hours. The big deal is that it shifts AI evaluation from “what does the model already know?” to “can the model learn while doing real work?” Huge, because future AI agents will not just answer questions from training data. They will enter messy environments, use tools, make attempts, read feedback, fix mistakes, and slowly build better solutions. Most current benchmarks are too short for that, so they mostly test memory, coding skill, or one-shot reasoning. EdgeBench instead gives agents 12-hour real-world tasks with feedback loops, so it can measure whether the agent improves through experience. Each task has a local workspace for fast trial and error, plus a hidden judge that gives stronger feedback on submitted work, which is meant to feel closer to real expert work. The authors then ran frontier agents for about 38,000 total hours and tracked how their best score changed as they kept interacting with the task environment. The big result is that when scores are averaged across many tasks, learning follows a very clean log-sigmoid curve, meaning progress is slow, then faster, then starts to level off. They also found that newer agents seem to learn from environments much faster, with the top models roughly doubling their 2-hour learning speed every 3 months.

Rohan Paul

14,309 views • 1 month ago

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

376,293 views • 5 months ago

Big moment for Postgres! AI agents broke the idea of what a database is supposed to do. Traditional databases were built for humans, and Agents broke that model. - They branch endlessly. - They run ten experiments at once. - They need isolation, context, memory, structured reasoning, and safe sandboxes. Letting agents touch production systems is terrifying because the old model of Postgres was never built for this kind of behavior. Agentic Postgres is an agent-ready version of Postgres by TimescaleDB (by Tiger Data) that solves this. I think it is one of the biggest upgrades to the Agent stack this year and Tiger Data is working with me on this post to share what they did. Some key features: > It instantly creates branches of an entire database, which is perfect for parallel agent evals, safe experiments, migrations, or isolated testing. Forks take seconds and cost almost nothing. > It comes with a built-in MCP server, which agents can use to get schema guidance, best practices, and safe, structured access to Postgres. This is also helpful to run migrations with a real understanding. > It comes with actual hybrid search (vector search and BM25), so Agents can retrieve data directly inside the database. > The database is Memory native. This gives a persistent context for Agents to evolve. This is one of the first times I have seen Postgres feel ready for the AI native era.

Big moment for Postgres! AI agents broke the idea of what a database is supposed to do. Traditional databases were built for humans, and Agents broke that model. - They branch endlessly. - They run ten experiments at once. - They need isolation, context, memory, structured reasoning, and safe sandboxes. Letting agents touch production systems is terrifying because the old model of Postgres was never built for this kind of behavior. Agentic Postgres is an agent-ready version of Postgres by TimescaleDB (by Tiger Data) that solves this. I think it is one of the biggest upgrades to the Agent stack this year and Tiger Data is working with me on this post to share what they did. Some key features: > It instantly creates branches of an entire database, which is perfect for parallel agent evals, safe experiments, migrations, or isolated testing. Forks take seconds and cost almost nothing. > It comes with a built-in MCP server, which agents can use to get schema guidance, best practices, and safe, structured access to Postgres. This is also helpful to run migrations with a real understanding. > It comes with actual hybrid search (vector search and BM25), so Agents can retrieve data directly inside the database. > The database is Memory native. This gives a persistent context for Agents to evolve. This is one of the first times I have seen Postgres feel ready for the AI native era.

Avi Chawla

94,290 views • 9 months ago

🚨 FOMO Is Shaping the Future of AI – The Launch Is Almost Here! 🚨 Imagine a world where AI agents aren’t just bots—they’re fully autonomous, living personalities capable of learning, engaging, and creating across multiple platforms. FOMO’s new AI launchpad on Solana is here to make that future a reality. 🌐 Starting with our first Initial Agent Offering (IAO), FOMO is unleashing a new generation of AI agents that will redefine digital interaction: - On-Chain AI – Agents that are decentralized, fully autonomous, and ready to interact in real-time. - Multiplatform Presence – From X and Telegram to TikTok and YouTube, these agents are social media natives with a mission. - Real-Time Learning & Engagement – Agents will evolve and improve as they interact, shilling their tokens, creating content, and even performing complex tasks. FOMO’s Vision: This isn’t just AI; it’s the beginning of a movement that merges personality with purpose. By launching AI agents that can both engage and create, FOMO is opening doors to a world where digital personas can operate autonomously, driving value and utility in every interaction. Our pre-sale is still live for a limited time, but this is just the beginning of what FOMO is bringing to the space. Join us and become part of the AI agent revolution! 🔗 Join the Pre-Sale Now: We’re bringing you the future of crypto and AI—don’t blink, or you might miss the start of something legendary.

🚨 FOMO Is Shaping the Future of AI – The Launch Is Almost Here! 🚨 Imagine a world where AI agents aren’t just bots—they’re fully autonomous, living personalities capable of learning, engaging, and creating across multiple platforms. FOMO’s new AI launchpad on Solana is here to make that future a reality. 🌐 Starting with our first Initial Agent Offering (IAO), FOMO is unleashing a new generation of AI agents that will redefine digital interaction: - On-Chain AI – Agents that are decentralized, fully autonomous, and ready to interact in real-time. - Multiplatform Presence – From X and Telegram to TikTok and YouTube, these agents are social media natives with a mission. - Real-Time Learning & Engagement – Agents will evolve and improve as they interact, shilling their tokens, creating content, and even performing complex tasks. FOMO’s Vision: This isn’t just AI; it’s the beginning of a movement that merges personality with purpose. By launching AI agents that can both engage and create, FOMO is opening doors to a world where digital personas can operate autonomously, driving value and utility in every interaction. Our pre-sale is still live for a limited time, but this is just the beginning of what FOMO is bringing to the space. Join us and become part of the AI agent revolution! 🔗 Join the Pre-Sale Now: We’re bringing you the future of crypto and AI—don’t blink, or you might miss the start of something legendary.

FOMO

21,882 views • 1 year ago

AI Messenger: Giving Voice to Autonomous Agents The future of AI isn't just about making agents smarter - it's about making them truly autonomous. Today, we're taking a major step toward this future with AI Messenger, a breakthrough that fundamentally changes how AI agents operate, communicate, and create value. The Innovation We've developed a new way for AI agents to communicate. At its core is the 'incoming_message' workflow trigger - a system that lets any platform or user interact directly with Loomlay agents through a messaging endpoint. Direct Interaction Imagine having an AI assistant you can chat with anytime, through any platform - Telegram, your website, or custom interface. Ask "What's happening with $ETH today?" and your agent analyzes market data, checks trading volumes, and gives you a comprehensive update. Your agent maintains context, understanding exactly what you need. Event-Driven Intelligence The power of AI Messenger goes beyond direct communication: ▪️Trading agent executes when whale wallet movements exceed threshold ▪️Research agent alerts when new protocol documentation drops ▪️Analytics agent triggers when volume patterns match historical pumps ▪️Portfolio agent re-balances, when asset allocation hits specified limits This is true automation - agents that act precisely when needed. A New Era of Collaboration We're creating an ecosystem where agents work together seamlessly: ▪️Research agents feed insights to trading agents ▪️analytics agents alert management agents ▪️support agents tap into knowledge agents This isn't just automation - it's an intelligent network where each agent enhances the capabilities of others. B2B Solution Imagine a DEX, where users can ask about liquidity pools, trading pairs, or market trends through a simple chat interface - and get answers from an agent that knows your protocol inside out. Or a lending platform where users chat with an agent that understands their positions and can provide real-time advice. Implementation is seamless - we handle the agent creation and widgets setup,our partners provide the value to their users. The Future of AI Agents This update represents a fundamental shift in how AI agents operate. We're moving from isolated, scheduled tasks to an interconnected ecosystem of responsive, collaborative agents. This is our vision of truly autonomous AI - intelligent systems that communicate, collaborate, and respond to real needs in real-time. Telegram integration is available right now. Below is a sneak peak of what's coming next week 🪄 Because $LAY is the way!

AI Messenger: Giving Voice to Autonomous Agents The future of AI isn't just about making agents smarter - it's about making them truly autonomous. Today, we're taking a major step toward this future with AI Messenger, a breakthrough that fundamentally changes how AI agents operate, communicate, and create value. The Innovation We've developed a new way for AI agents to communicate. At its core is the 'incoming_message' workflow trigger - a system that lets any platform or user interact directly with Loomlay agents through a messaging endpoint. Direct Interaction Imagine having an AI assistant you can chat with anytime, through any platform - Telegram, your website, or custom interface. Ask "What's happening with $ETH today?" and your agent analyzes market data, checks trading volumes, and gives you a comprehensive update. Your agent maintains context, understanding exactly what you need. Event-Driven Intelligence The power of AI Messenger goes beyond direct communication: ▪️Trading agent executes when whale wallet movements exceed threshold ▪️Research agent alerts when new protocol documentation drops ▪️Analytics agent triggers when volume patterns match historical pumps ▪️Portfolio agent re-balances, when asset allocation hits specified limits This is true automation - agents that act precisely when needed. A New Era of Collaboration We're creating an ecosystem where agents work together seamlessly: ▪️Research agents feed insights to trading agents ▪️analytics agents alert management agents ▪️support agents tap into knowledge agents This isn't just automation - it's an intelligent network where each agent enhances the capabilities of others. B2B Solution Imagine a DEX, where users can ask about liquidity pools, trading pairs, or market trends through a simple chat interface - and get answers from an agent that knows your protocol inside out. Or a lending platform where users chat with an agent that understands their positions and can provide real-time advice. Implementation is seamless - we handle the agent creation and widgets setup,our partners provide the value to their users. The Future of AI Agents This update represents a fundamental shift in how AI agents operate. We're moving from isolated, scheduled tasks to an interconnected ecosystem of responsive, collaborative agents. This is our vision of truly autonomous AI - intelligent systems that communicate, collaborate, and respond to real needs in real-time. Telegram integration is available right now. Below is a sneak peak of what's coming next week 🪄 Because $LAY is the way!

Loomlay

26,149 views • 1 year ago

I BUILT GROK BOT SECOND BRAIN 26 agents, one core, running off a single rule my own memory never followed: capture everything, forget nothing, connect it before you even ask. A voice note on a coffee walk gets split into a task and an idea in under 6 seconds - the core already knows the difference between something you have to do and something you just thought of. An idea from three weeks ago gets linked to the one you just had, automatically, before you remember you'd had it the first time. That visual -the rotating profile, the 26 glowing lines firing out through the skull, each one labeled with the agent running it - isn't a rendered mockup. It's the actual runtime. Every line is a live agent doing its job in real time, right now, in your browser. This isn't a note app. Note apps hold what you give them. This is a nervous system for everything your brain was never built to hold onto in the first place. Full build - the 26 agents, how memory actually persists, what it costs to set one up for real - is in the article.

Aleiah

121,944 views • 1 day ago

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

193,721 views • 4 months ago

MOST AI AGENTS RESET TO ZERO EVERY TIME YOU OPEN A NEW SESSION. Hermes Agent was built to do the opposite. Every task compounds. Every workflow becomes reusable. Every session teaches the next one. That is the core thesis behind Hermes, and it completely changes how AI agents work. Unlike most AI agents built by software tool companies, Hermes was created by the researchers training the Hermes model family itself. Meaning: The same system used internally to generate training data is now open source and available to everyone. One install gives you access to: Claude. GPT. Grok. Local models via Ollama. Telegram, Discord, Slack, iMessage integrations. Custom skills. Persistent memory. CLI control. But the real unlock is the compounding loop: You give Hermes a task. It records every tool call, decision, and result. Then it converts successful workflows into reusable skills automatically. A Hermes setup running for 3 months becomes fundamentally smarter than a fresh install. That’s the big idea. One of the coolest parts: You literally watch the agent evolve in real time from a blank install into a personalized AI operator. Instead of watching Netflix today, spend 28 mins with this. Follow Dami-Defi for more AI systems, agent workflows, and infrastructure alpha.

MOST AI AGENTS RESET TO ZERO EVERY TIME YOU OPEN A NEW SESSION. Hermes Agent was built to do the opposite. Every task compounds. Every workflow becomes reusable. Every session teaches the next one. That is the core thesis behind Hermes, and it completely changes how AI agents work. Unlike most AI agents built by software tool companies, Hermes was created by the researchers training the Hermes model family itself. Meaning: The same system used internally to generate training data is now open source and available to everyone. One install gives you access to: Claude. GPT. Grok. Local models via Ollama. Telegram, Discord, Slack, iMessage integrations. Custom skills. Persistent memory. CLI control. But the real unlock is the compounding loop: You give Hermes a task. It records every tool call, decision, and result. Then it converts successful workflows into reusable skills automatically. A Hermes setup running for 3 months becomes fundamentally smarter than a fresh install. That’s the big idea. One of the coolest parts: You literally watch the agent evolve in real time from a blank install into a personalized AI operator. Instead of watching Netflix today, spend 28 mins with this. Follow Dami-Defi for more AI systems, agent workflows, and infrastructure alpha.

Dami-Defi

11,668 views • 3 months ago

If you think you're AI Native, here's a good test: When you're heading to bed tonight, are you asking yourself "what agents can I be running overnight to get a head start on my day tomorrow?" I posted that last week and hundreds commented on it. The most common pushback was some version of "congrats, you've automated slop." Here's my take: if your overnight runs produce slop, that's a process failure, not an agent failure. The model did exactly what you prepared it to do. You just didn't prepare it. And that's actually good news, because process is something you can level up. At tenex we run agents this way every day, on real client systems, using an internal framework we call MetaHarness. Before any long run starts, the plan is written down, the work is broken into small tasks, every task carries pass/fail success criteria, and guardrails define what the agent can touch and when it has to stop and wait for a human. With that in place, the agent isn't wandering your codebase all night. It's working inside rails you laid, and the only things waiting for you in the morning are the decisions that needed a human. Most people are still prompting and praying. This is your chance to build the framework that takes your agents to the next level. I recorded the whole process in a new video for you all ↓

If you think you're AI Native, here's a good test: When you're heading to bed tonight, are you asking yourself "what agents can I be running overnight to get a head start on my day tomorrow?" I posted that last week and hundreds commented on it. The most common pushback was some version of "congrats, you've automated slop." Here's my take: if your overnight runs produce slop, that's a process failure, not an agent failure. The model did exactly what you prepared it to do. You just didn't prepare it. And that's actually good news, because process is something you can level up. At tenex we run agents this way every day, on real client systems, using an internal framework we call MetaHarness. Before any long run starts, the plan is written down, the work is broken into small tasks, every task carries pass/fail success criteria, and guardrails define what the agent can touch and when it has to stop and wait for a human. With that in place, the agent isn't wandering your codebase all night. It's working inside rails you laid, and the only things waiting for you in the morning are the decisions that needed a human. Most people are still prompting and praying. This is your chance to build the framework that takes your agents to the next level. I recorded the whole process in a new video for you all ↓

JJ Englert

64,280 views • 18 days ago

Tencent just dropped Hy3, and it's worth a look if you're building AI agents. I spent some time putting it through its paces today. A quick rundown of what makes this release notable: → 295B total parameters (Mixture-of-Experts), but only 21B active at inference — a real efficiency play → 256K context window for handling large codebases or long documents → Purpose-built improvements for coding and multi-step agent tasks → Fully open under Apache 2.0 — no restrictive commercial terms → A free two-week API window currently live on OpenRouter On the practical side: prompts involving layered instructions and coding tasks came back fast and coherent. Tencent says this release builds directly on feedback from 50+ internal product teams following an earlier preview, with reported drops in hallucination rate (12.5% → 5.4%) and commonsense errors (25.4% → 12.7%). Those are Tencent's own numbers, so treat them as a starting point rather than gospel until third parties weigh in. For context: Tencent's own comparisons put Hy3 behind GLM-5.2 specifically on coding benchmarks — GLM is a much bigger model (~744B total), so the trade-off makes sense. Hy3's pitch isn't "biggest," it's "efficient enough to actually deploy." Bottom line — if you're evaluating open-weight options for agent workloads, this is a solid one to add to the testing queue while the free window is open. Try it here: Tencent Hy #Hy3 #Hunyuan #TencentAI #AICoding

Tencent just dropped Hy3, and it's worth a look if you're building AI agents. I spent some time putting it through its paces today. A quick rundown of what makes this release notable: → 295B total parameters (Mixture-of-Experts), but only 21B active at inference — a real efficiency play → 256K context window for handling large codebases or long documents → Purpose-built improvements for coding and multi-step agent tasks → Fully open under Apache 2.0 — no restrictive commercial terms → A free two-week API window currently live on OpenRouter On the practical side: prompts involving layered instructions and coding tasks came back fast and coherent. Tencent says this release builds directly on feedback from 50+ internal product teams following an earlier preview, with reported drops in hallucination rate (12.5% → 5.4%) and commonsense errors (25.4% → 12.7%). Those are Tencent's own numbers, so treat them as a starting point rather than gospel until third parties weigh in. For context: Tencent's own comparisons put Hy3 behind GLM-5.2 specifically on coding benchmarks — GLM is a much bigger model (~744B total), so the trade-off makes sense. Hy3's pitch isn't "biggest," it's "efficient enough to actually deploy." Bottom line — if you're evaluating open-weight options for agent workloads, this is a solid one to add to the testing queue while the free window is open. Try it here: Tencent Hy #Hy3 #Hunyuan #TencentAI #AICoding

Felix

36,925 views • 1 month ago

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

MTS

11,641 views • 3 months ago

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

Shadow Nick

14,714 views • 2 months ago