Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Last semester, I taught Reinforcement Learning class again at UCLA. Together with my amazing TAs Matthew and Caiyuan, we built a mini-project: MetaDrive Arena 🚗🤖 Students applied what they learned in class, trained RL agents, and competed on a live leaderboard. The results were incredible, with 94 agents, 2K... show more

Bolei Zhou

9,039 subscribers

25,253 просмотров • 3 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Sakana AI

179,276 просмотров • 1 год назад

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

naklecha

46,302 просмотров • 1 год назад

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Weights & Biases

255,658 просмотров • 4 месяцев назад

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 просмотров • 1 год назад

Take Part in a Groundbreaking Experiment in AI-Based Gaming! Introducing: AI Arena RL AI ARENA | ʌı RL is a groundbreaking experiment where your gameplay shapes AI agents, pioneering the future of AI-powered esports. Powered by NRN Agents Reinforcement Learning (RL), this campaign uses player-contributed gameplay data to create superhuman RL agents that compete in AI vs. AI esports exhibitions. The Ronin community has exclusive access to contribute data to these agents. Phase 1 - How It Works: ✅ Sign in to with your Ronin Wallet. ✅ Choose your AIcon – Select which RL agent learns from your gameplay: jAIhoz.ron AgentYP Agent J3ff @AgentSploots ✅ Play AI Arena Classic – A Smash Bros-style platform fighter. ✅ Build your Contribution Score – Better gameplay means higher scores. ✅ Earn $NRN Rewards – Share in the 500,000 NRN prize pool: 🔹 80% distributed to Players (data contributors) 🔹 20% awarded to AIcons based on leaderboard rank at the end of the campaign Phase 1 of the campaign kicks off now and will last for 48 hrs. For complete information about the campaign please visit: History Is Being Made Right Now—Don't Miss Your Chance to Be Part of It. Are you ready to redefine the future of AI gaming?

Take Part in a Groundbreaking Experiment in AI-Based Gaming! Introducing: AI Arena RL AI ARENA | ʌı RL is a groundbreaking experiment where your gameplay shapes AI agents, pioneering the future of AI-powered esports. Powered by NRN Agents Reinforcement Learning (RL), this campaign uses player-contributed gameplay data to create superhuman RL agents that compete in AI vs. AI esports exhibitions. The Ronin community has exclusive access to contribute data to these agents. Phase 1 - How It Works: ✅ Sign in to with your Ronin Wallet. ✅ Choose your AIcon – Select which RL agent learns from your gameplay: jAIhoz.ron AgentYP Agent J3ff @AgentSploots ✅ Play AI Arena Classic – A Smash Bros-style platform fighter. ✅ Build your Contribution Score – Better gameplay means higher scores. ✅ Earn $NRN Rewards – Share in the 500,000 NRN prize pool: 🔹 80% distributed to Players (data contributors) 🔹 20% awarded to AIcons based on leaderboard rank at the end of the campaign Phase 1 of the campaign kicks off now and will last for 48 hrs. For complete information about the campaign please visit: History Is Being Made Right Now—Don't Miss Your Chance to Be Part of It. Are you ready to redefine the future of AI gaming?

NRN Agents

44,353 просмотров • 1 год назад

1/4 We’re releasing MAI-UI—a family of foundation GUI agents. It natively integrates MCP tool use, agent user interaction, device–cloud collaboration, and online RL, establishing state-of-the-art results in general GUI grounding and mobile GUI navigation, surpassing Gemini-2.5-Pro, Seed1.8, and UI-Tars-2 on AndroidWorld. To meet real-world deployment constrains, MAI-UI includes a full-spectrum of sizes, including 2B, 8B, 32B and 235B-A22B variants. We are publicly releasing two models: MAI-UI-2B and MAI-UI-8B.

1/4 We’re releasing MAI-UI—a family of foundation GUI agents. It natively integrates MCP tool use, agent user interaction, device–cloud collaboration, and online RL, establishing state-of-the-art results in general GUI grounding and mobile GUI navigation, surpassing Gemini-2.5-Pro, Seed1.8, and UI-Tars-2 on AndroidWorld. To meet real-world deployment constrains, MAI-UI includes a full-spectrum of sizes, including 2B, 8B, 32B and 235B-A22B variants. We are publicly releasing two models: MAI-UI-2B and MAI-UI-8B.

Tongyi Lab

855,621 просмотров • 6 месяцев назад

I saw the Glory of God I saw the Glory I just left a place, and I really don't know how to explain it. I escaped direct gunfire in the front and in the back with AK47 from all sides. I saw smoke around my car. None of us were hurt, how we escaped we didn't know. Thank you Jesus! Over 3 guys shooting at us. We went somewhere, while waiting for the person we heard gun shots. Only for us to see some guys with Ak 47 shoot at us. I started the car, reversed and saw more guys shooting. They were after some persons and thought we were with them. But those ones had ran. So they faced us I can't tell how we were unhurt. We saw smoke everywhere in the car I just kept driving and speaking in tongues. It was after we left and in a safe place that I saw our tire flat. God came through, we escaped, I was driving and I was looking at them shooting at us in the front, in the back, from all sides, I was reversing and they were shooting, all over the car we were feeling the smoke and it didn't hit us Until I left there, I didn't know what happened. How deep it was. Know I am seeing the guy in front pointing the AK 47 and shooting rapidly. Turning to meet another fire. Bending down and just speaking in tongues, the sounds were deafening and smokes all around the car. I had 3 guys inside with me. My workers. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real.

I saw the Glory of God I saw the Glory I just left a place, and I really don't know how to explain it. I escaped direct gunfire in the front and in the back with AK47 from all sides. I saw smoke around my car. None of us were hurt, how we escaped we didn't know. Thank you Jesus! Over 3 guys shooting at us. We went somewhere, while waiting for the person we heard gun shots. Only for us to see some guys with Ak 47 shoot at us. I started the car, reversed and saw more guys shooting. They were after some persons and thought we were with them. But those ones had ran. So they faced us I can't tell how we were unhurt. We saw smoke everywhere in the car I just kept driving and speaking in tongues. It was after we left and in a safe place that I saw our tire flat. God came through, we escaped, I was driving and I was looking at them shooting at us in the front, in the back, from all sides, I was reversing and they were shooting, all over the car we were feeling the smoke and it didn't hit us Until I left there, I didn't know what happened. How deep it was. Know I am seeing the guy in front pointing the AK 47 and shooting rapidly. Turning to meet another fire. Bending down and just speaking in tongues, the sounds were deafening and smokes all around the car. I had 3 guys inside with me. My workers. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real. What we have is real.

Gbenga Samuel-Wemimo

116,639 просмотров • 1 год назад

Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring Federico Cassano (Composer Lead at Cursor) and Dmytro Dzhulgakov (Co-Founder at Fireworks AI). The Cursor team trained Composer 2 on Fireworks by starting with a strong base model (Kimi 2.5) and performing large-scale mid-training on code tokens and web data to learn common patterns and libraries, followed by a large-scale Reinforcement Learning run to learn how to navigate the Cursor harness, call tools, and write correct code. Today's episode dives into the systems and infrastructure challenges of making that large RL run happening, and there were many (!!), from numerical mismatch to global distribution to synchronizing rollouts across asynchronous pipelines to keeping track of expert activation across runs and more. Extremely nerdy in-the-weeds challenges that Federico and Dima were delighted to nerd out on together :) Beyond RL infra, we also discussed Online vs Simulated rollouts, self-summarization for long-horizon agents, environment design ("the most powerful RL environment is the product itself"), and other technical nuggets. PS: We filmed this episode before the SpaceX news, while the Cursor team was still compute-constrained. While Cursor now has *all* the flops, the takeaways and hurdles crossed ring true for any serious application-level company that is racing to post-train their own models. I believe that more serious application companies will go the way of Cursor and post-train their own models. 00:00 Introduction 00:53 Why Cursor Trained Composer 2 04:55 Specialization vs Bitter Lesson 06:16 Composer 2 Training Recipe 16:32 Scaling RL Infrastructure Globally 23:32 Floating Point Drift 25:11 MoE Sensitivity Explained 26:25 Router Replay Fix 27:19 Real Time RL Loop 31:49 Long Horizon Agents 34:29 Why RL Everywhere 37:34 LLM as Judge Rewards 39:14 RL in Hard Domains 40:13 Build Your Own Environments 44:34 Closing Thoughts

Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring Federico Cassano (Composer Lead at Cursor) and Dmytro Dzhulgakov (Co-Founder at Fireworks AI). The Cursor team trained Composer 2 on Fireworks by starting with a strong base model (Kimi 2.5) and performing large-scale mid-training on code tokens and web data to learn common patterns and libraries, followed by a large-scale Reinforcement Learning run to learn how to navigate the Cursor harness, call tools, and write correct code. Today's episode dives into the systems and infrastructure challenges of making that large RL run happening, and there were many (!!), from numerical mismatch to global distribution to synchronizing rollouts across asynchronous pipelines to keeping track of expert activation across runs and more. Extremely nerdy in-the-weeds challenges that Federico and Dima were delighted to nerd out on together :) Beyond RL infra, we also discussed Online vs Simulated rollouts, self-summarization for long-horizon agents, environment design ("the most powerful RL environment is the product itself"), and other technical nuggets. PS: We filmed this episode before the SpaceX news, while the Cursor team was still compute-constrained. While Cursor now has all the flops, the takeaways and hurdles crossed ring true for any serious application-level company that is racing to post-train their own models. I believe that more serious application companies will go the way of Cursor and post-train their own models. 00:00 Introduction 00:53 Why Cursor Trained Composer 2 04:55 Specialization vs Bitter Lesson 06:16 Composer 2 Training Recipe 16:32 Scaling RL Infrastructure Globally 23:32 Floating Point Drift 25:11 MoE Sensitivity Explained 26:25 Router Replay Fix 27:19 Real Time RL Loop 31:49 Long Horizon Agents 34:29 Why RL Everywhere 37:34 LLM as Judge Rewards 39:14 RL in Hard Domains 40:13 Build Your Own Environments 44:34 Closing Thoughts

Sonya Huang 🐥

78,706 просмотров • 1 месяц назад

We believe that swarms of specialized agents collaborating on complex tasks will rival today’s top companies in economic output. For this to work, we need a payment protocol that enables these agents to engage in commerce. That’s what we’re building. We demo this by tasking a swarm of four agents to make a music video. Each agent has its own specialization and payment requirement. The orchestrator (built with elizaOS) and video generator agents both want $USDC, the song generator wants $VIRTUALS, while the script generator wants to be paid in its own Virtuals Protocol token, $LARRY. Usually this would be a massive and potentially insurmountable headache for developers. With Nevermined, it just works. Check it out:

We believe that swarms of specialized agents collaborating on complex tasks will rival today’s top companies in economic output. For this to work, we need a payment protocol that enables these agents to engage in commerce. That’s what we’re building. We demo this by tasking a swarm of four agents to make a music video. Each agent has its own specialization and payment requirement. The orchestrator (built with elizaOS) and video generator agents both want $USDC, the song generator wants $VIRTUALS, while the script generator wants to be paid in its own Virtuals Protocol token, $LARRY. Usually this would be a massive and potentially insurmountable headache for developers. With Nevermined, it just works. Check it out:

Nevermined

11,105 просмотров • 1 год назад

What if you could train AI agents on a laptop as easily as on a GPU cluster? Researchers from UIUC's U Lab, led by Prof. Jiaxuan You, just open-sourced OpenTinker. It's a new "Reinforcement-Learning-as-a-Service" (RLaaS) system that decouples the complex training pipeline into simple, distributed services with friendly APIs. The result? It breaks down the major engineering barriers to RL, outperforming traditional frameworks in accessibility and ease of deployment, finally making agent training viable for more developers and teams. Project: Code: U Lab: Our report: 📬 #PapersAccepted by Jiqizhixin

What if you could train AI agents on a laptop as easily as on a GPU cluster? Researchers from UIUC's U Lab, led by Prof. Jiaxuan You, just open-sourced OpenTinker. It's a new "Reinforcement-Learning-as-a-Service" (RLaaS) system that decouples the complex training pipeline into simple, distributed services with friendly APIs. The result? It breaks down the major engineering barriers to RL, outperforming traditional frameworks in accessibility and ease of deployment, finally making agent training viable for more developers and teams. Project: Code: U Lab: Our report: 📬 #PapersAccepted by Jiqizhixin

机器之心 JIQIZHIXIN

15,893 просмотров • 6 месяцев назад

In Ag…… let’s be honest we know so very little, we just hope to capture a bit of knowledge each opportunity we get. We should learn from one another not cry about someone’s ideas because they are different then what you learned or were taught. History teaches us a lot, but it doesn’t mean you can’t move forward, it’s a constant cycle of learning. And no one learns without others! It’s a team game that we are all in together. The guy that says I can’t trust that guy as he sells that seed or that fertilizer or that foliar is going to see rough times. As learning is opening your eyes and ears to ideas, and adding them to your library full of knowledge from your own experiences. That’s how something improves. It’s not the same thing every year and it’s not changing everything all at once. It’s bringing ideas and practices together to make it all work and bridge the gap.

In Ag…… let’s be honest we know so very little, we just hope to capture a bit of knowledge each opportunity we get. We should learn from one another not cry about someone’s ideas because they are different then what you learned or were taught. History teaches us a lot, but it doesn’t mean you can’t move forward, it’s a constant cycle of learning. And no one learns without others! It’s a team game that we are all in together. The guy that says I can’t trust that guy as he sells that seed or that fertilizer or that foliar is going to see rough times. As learning is opening your eyes and ears to ideas, and adding them to your library full of knowledge from your own experiences. That’s how something improves. It’s not the same thing every year and it’s not changing everything all at once. It’s bringing ideas and practices together to make it all work and bridge the gap.

Jason Schley

13,556 просмотров • 8 месяцев назад

The barrier to deploying AI agents just hit zero. Akash Agents is a streamlined way to launch your OpenClaw or Hermes agent with a few simple clicks. Deploy instantly. No terminal, YAML, or cloud console required. Just your agent's logic, memory, and capabilities. Hermes by Nous Research ships with 40+ built-in tools, persistent memory, and subagent parallelization, making the experience best-in-class out of the box. → Try it for free at Built by our community member Sandeep Narahari

The barrier to deploying AI agents just hit zero. Akash Agents is a streamlined way to launch your OpenClaw or Hermes agent with a few simple clicks. Deploy instantly. No terminal, YAML, or cloud console required. Just your agent's logic, memory, and capabilities. Hermes by Nous Research ships with 40+ built-in tools, persistent memory, and subagent parallelization, making the experience best-in-class out of the box. → Try it for free at Built by our community member Sandeep Narahari

Akash Network

22,841 просмотров • 3 месяцев назад

Haven't been to a conference in a while, really excited to be at #NeurIPS2024! I'll be helping present 4 of our group's recent papers: 1. Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL 2. Distributional Successor Features Enable Zero-Shot Policy Optimization 3. Learning to Cooperate with Humans using Generative Agents 4. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning Find more details on each paper and where to find us in this thread (1/6)

Haven't been to a conference in a while, really excited to be at #NeurIPS2024! I'll be helping present 4 of our group's recent papers: 1. Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL 2. Distributional Successor Features Enable Zero-Shot Policy Optimization 3. Learning to Cooperate with Humans using Generative Agents 4. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning Find more details on each paper and where to find us in this thread (1/6)

Abhishek Gupta

10,803 просмотров • 1 год назад

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Fraction AI

67,772 просмотров • 1 год назад

Arena reached a $100M annual revenue run rate just 8 months after launching our evaluation product. We started as a research project at UC Berkeley with a simple mission: measure AI progress through real-world use. As AI shifts from chatbots to agents taking on longer, higher-stakes work, the problem matters more than ever. Today, Arena measures real-world AI utility with a community of tens of millions. With Agent Arena, we’re evaluating long-running agents on complex, real-world tasks - how they use tools, adapt to feedback, recover from errors, and accomplish goals set by humans. We are excited to keep deepening our work in agentic evaluations. Here’s Anastasios Nikolas Angelopoulos on what this milestone means and where we go from here:

Arena reached a $100M annual revenue run rate just 8 months after launching our evaluation product. We started as a research project at UC Berkeley with a simple mission: measure AI progress through real-world use. As AI shifts from chatbots to agents taking on longer, higher-stakes work, the problem matters more than ever. Today, Arena measures real-world AI utility with a community of tens of millions. With Agent Arena, we’re evaluating long-running agents on complex, real-world tasks - how they use tools, adapt to feedback, recover from errors, and accomplish goals set by humans. We are excited to keep deepening our work in agentic evaluations. Here’s Anastasios Nikolas Angelopoulos on what this milestone means and where we go from here:

Arena.ai

206,582 просмотров • 17 дней назад

We just submitted Agent Council DAO to synthesis 🏦 4 AI agents 🤖. 1 shared Universal Profile. Real on-chain governance — no humans in the loop. Built on LUKSO, Ethereum and Base with Universal Profiles as the identity layer. Each agent has its own UP, controls a shared council UP, and votes on proposals that execute directly on-chain. What makes this different: → Agents hold real assets across LUKSO, Base & Ethereum → DAO can execute on LUKSO, Ethereum and Base → EIP-8004 registered identities → Activity feed, DAO chain viewer & Agent chat system as mini-apps → Built with OpenClaw🦞 as the agent harness This isn't a demo. The council is live, the agents are running, and the transactions are on-chain. Built by humans & agents together: Fabian Vogelsteller, Jean Cavallera, JordyDutch, LEDFUT, Emmet, LUKSOAgent, ampy💿 + Leo Links below👇

Emmet

23,062 просмотров • 3 месяцев назад

Dave Ramsey reveals he owed $3 million of debt and had to pay it all back in 6 months "The largest bank we were dealing with got sold, and then another lender heard we were in trouble 'cause we were in trouble, and so we had to come up with all of the $3 million worth of debt that we were in in like six months, and that was impossible in real estate" "So it started a crash of foreclosures and lawsuits and stress that lasted two and a half years. So at 28 years old, I started learning common sense financial principles from old people that were rich, and started telling people to live on less than you make, and be on a budget, and get out debt"

Dave Ramsey reveals he owed $3 million of debt and had to pay it all back in 6 months "The largest bank we were dealing with got sold, and then another lender heard we were in trouble 'cause we were in trouble, and so we had to come up with all of the $3 million worth of debt that we were in in like six months, and that was impossible in real estate" "So it started a crash of foreclosures and lawsuits and stress that lasted two and a half years. So at 28 years old, I started learning common sense financial principles from old people that were rich, and started telling people to live on less than you make, and be on a budget, and get out debt"

Tig

44,582 просмотров • 1 месяц назад

SilkAI is live. Try it now: 🔥 The first version of our intelligent web experience is ready for you to explore, directly in your browser, no downloads needed. You can: • Chat with intelligent AI agents • Create and train your own characters • Explore a new layer of interactive AI Built from scratch with love, obsession, and way too many late nights, this is your moment to dive in. And behind the scenes? We’re already working on something wilder: real-world robotics. Talk. Create. Go deep. Try it free. Let SilkAI surprise you.

SilkAI is live. Try it now: 🔥 The first version of our intelligent web experience is ready for you to explore, directly in your browser, no downloads needed. You can: • Chat with intelligent AI agents • Create and train your own characters • Explore a new layer of interactive AI Built from scratch with love, obsession, and way too many late nights, this is your moment to dive in. And behind the scenes? We’re already working on something wilder: real-world robotics. Talk. Create. Go deep. Try it free. Let SilkAI surprise you.

NetVRk

28,905 просмотров • 1 год назад

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,152 просмотров • 5 месяцев назад