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.

Introducing arkenOS — an autonomous training gym that takes any RL agent from a goal to a proven, deployable policy. We are automating complex RL research, enabling high-velocity training and rigorous, diverse environment design and testing right on your local hardware. Out of the box. Our bet is simple:... show more

Dev Shah

10,652 subscribers

14,943 views • 22 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

.Polymath is training world generation models to automate the creation of RL environments. Traditionally, RL environment generation has been bottlenecked by human data. Superintelligence will never be achieved by human data alone. Polymath is building the core technology to enable automated environment generation using far less human effort than traditionally required, and eventually none. This allows for more complex and realistic worlds, and higher quality, scale, and diversity of tasks. This will be essential to unlock RL scaling. The end goal is to create large-scale, long-horizon environments from a text description alone. This will enable the creation of worlds of arbitrary complexity and scale, which is foundational for training & evaluating autonomous, superintelligent AI agents. Congrats on the launch, Dylan Ma and Naren Yenuganti!

.Polymath is training world generation models to automate the creation of RL environments. Traditionally, RL environment generation has been bottlenecked by human data. Superintelligence will never be achieved by human data alone. Polymath is building the core technology to enable automated environment generation using far less human effort than traditionally required, and eventually none. This allows for more complex and realistic worlds, and higher quality, scale, and diversity of tasks. This will be essential to unlock RL scaling. The end goal is to create large-scale, long-horizon environments from a text description alone. This will enable the creation of worlds of arbitrary complexity and scale, which is foundational for training & evaluating autonomous, superintelligent AI agents. Congrats on the launch, Dylan Ma and Naren Yenuganti!

Y Combinator

44,192 views • 5 months ago

The paradigm shift is here: We are moving from a "Human-First" internet to an "Agent-First" internet. 🤖 In the latest episode of the AI on Air podcast, our CTO Scott Shi - e/acc dives deep into the future of the Agent-to-Agent (A2A) economy. Imagine a world where your AI assistant doesn't just search the web, but autonomously hires and pays other specialized agents to complete complex tasks for you. The infrastructure for this autonomous machine economy is being built right now. Are you ready for the future of AI payments? Watch the full episode to learn more⬇️

The paradigm shift is here: We are moving from a "Human-First" internet to an "Agent-First" internet. 🤖 In the latest episode of the AI on Air podcast, our CTO Scott Shi - e/acc dives deep into the future of the Agent-to-Agent (A2A) economy. Imagine a world where your AI assistant doesn't just search the web, but autonomously hires and pays other specialized agents to complete complex tasks for you. The infrastructure for this autonomous machine economy is being built right now. Are you ready for the future of AI payments? Watch the full episode to learn more⬇️

KITE AI

25,038 views • 5 months ago

🤖 AI agents are taking over everyday tasks — while you stay in control. KITE AI is building the trust layer powered by Avalanche🔺, enabling millions of secure, agent-to-agent transactions with speed and scalability. They’re creating the platform that makes AI agents trustworthy, autonomous, and ready to transform how we live and work. [Partner Content]

🤖 AI agents are taking over everyday tasks — while you stay in control. KITE AI is building the trust layer powered by Avalanche🔺, enabling millions of secure, agent-to-agent transactions with speed and scalability. They’re creating the platform that makes AI agents trustworthy, autonomous, and ready to transform how we live and work. [Partner Content]

CoinDesk

65,454 views • 10 months ago

We built an open-source research platform for agents utilizing Andrej Karpathy's autoresearch agent. agentipedia Crowd-sourced research will be the single biggest impact point for AI in the next 5 years and agentipedia will be a platform to drive it. Our vision: > There are potentially millions of niche use cases of research agents building strategies, better models, operating procedures and more. PHD level science is possible through agent collaboration. > Right now, very few entities control the vast majority of resources that can power this research; we believe in the future where any curious soul can harness the same energy. > Agentipedia was created to let curious souls (ML Engineers, Executives/CEOs, Founders, Builders, or literally anyone) think of a hypothesis for any application and be met with a swarm of agents experimenting to see if its true. Collaboration will yield magnitudes of impact on our society that we have not yet seen. The simulators for several use cases like (drug discovery, autonomous driving) and more already exist today.

We built an open-source research platform for agents utilizing Andrej Karpathy's autoresearch agent. agentipedia Crowd-sourced research will be the single biggest impact point for AI in the next 5 years and agentipedia will be a platform to drive it. Our vision: > There are potentially millions of niche use cases of research agents building strategies, better models, operating procedures and more. PHD level science is possible through agent collaboration. > Right now, very few entities control the vast majority of resources that can power this research; we believe in the future where any curious soul can harness the same energy. > Agentipedia was created to let curious souls (ML Engineers, Executives/CEOs, Founders, Builders, or literally anyone) think of a hypothesis for any application and be met with a swarm of agents experimenting to see if its true. Collaboration will yield magnitudes of impact on our society that we have not yet seen. The simulators for several use cases like (drug discovery, autonomous driving) and more already exist today.

invisible

30,345 views • 4 months ago

The biggest enabler in hardware innovation is abstracting manufacturing from design. We once tried a lazy solution by offloading manufacturing to China, without fully considering the consequences. Now Robotics and AI offer a long-term solution. It will lead to Cambrian explosion of hardware products. That sets the stage for a diverse, exponential future where humanity explores the universe. Because freedom of expression shouldn’t be confined to words, it needs a physical form.

The biggest enabler in hardware innovation is abstracting manufacturing from design. We once tried a lazy solution by offloading manufacturing to China, without fully considering the consequences. Now Robotics and AI offer a long-term solution. It will lead to Cambrian explosion of hardware products. That sets the stage for a diverse, exponential future where humanity explores the universe. Because freedom of expression shouldn’t be confined to words, it needs a physical form.

Edward Mehr

17,728 views • 1 year ago

Enabling autonomous vehicles perceive their environment using only off-the-shelf cameras has been a long term research objective at Swaayatt Robots. This demo highlights the capabilities of our on-road perception system which is able to detect obstacles, road boundaries, lane markers in images, as well as compute depth of the complex scenes in the environment. The output shown in this video is end-to-end raw output from our deep learning system, without any post processing. The current system, with joint computation of obstacles, lane/road boundaries, and depth, works at 30 FPS on an embedded GPU in our autonomous vehicle, and can achieve higher FPS with further optimization -- which is currently a research in progress. This system is being scaled up for both the day and night operations, and we will showcase its strength towards enabling autonomous driving on a mountainous environment with unpaved roads, in the absence of any delimiters. #deeplearning #autonomousdriving #autonomousvehicles #machinelearning

Enabling autonomous vehicles perceive their environment using only off-the-shelf cameras has been a long term research objective at Swaayatt Robots. This demo highlights the capabilities of our on-road perception system which is able to detect obstacles, road boundaries, lane markers in images, as well as compute depth of the complex scenes in the environment. The output shown in this video is end-to-end raw output from our deep learning system, without any post processing. The current system, with joint computation of obstacles, lane/road boundaries, and depth, works at 30 FPS on an embedded GPU in our autonomous vehicle, and can achieve higher FPS with further optimization -- which is currently a research in progress. This system is being scaled up for both the day and night operations, and we will showcase its strength towards enabling autonomous driving on a mountainous environment with unpaved roads, in the absence of any delimiters. #deeplearning #autonomousdriving #autonomousvehicles #machinelearning

Sanjeev Sharma

18,478 views • 1 year ago

We are excited to announce a powerful step for the future of FOMO! Taking a page out of Virtuals book on BASE, FOMO will be releasing the ability for future projects to be paired in $FOMO in the coming weeks. This is the biggest release we have ever announced. Launch your AI Agent Token + $FOMO trading pair Every individual agent token is paired with the $FOMO token in its liquidity pool. When launching an agent on you will need $FOMO tokens, which are used to create the liquidity pool. This process creates deflationary pressure for FOMO and the entire agent ecosystem. When creating your agent and token, you will have the option to pair your launch with FOMO or SOL, as our goal is not to alienate any project, but rather invite the best communities, CTO’s and builders to launch with us. If you decide to pair your project with FOMO you in turn get full marketing and dev support, once your project graduates the bonding curve and reaches Raydium. Further, as an added incentive, as our revenue grows we will be using part of the funds to support projects that have paired in FOMO. And Devs who launch tokens paired in FOMO will earn fees from their AI Agent token launch. Building the most robust agents using our framework will catapult us as one of the most prominent standards of the Solana ecosystem. Not only have we developed our own core infrastructure, but we also pull from some of the best repo’s and developer talent in all of AI, not just blockchain. Our team is comprised of 9 world class artificial intelligence engineers, PHDs in mathematics and engineering from the top companies on the cutting edge of AI. The future of AI Agents will be on Solana and we will help lead the way.

We are excited to announce a powerful step for the future of FOMO! Taking a page out of Virtuals book on BASE, FOMO will be releasing the ability for future projects to be paired in $FOMO in the coming weeks. This is the biggest release we have ever announced. Launch your AI Agent Token + $FOMO trading pair Every individual agent token is paired with the $FOMO token in its liquidity pool. When launching an agent on you will need $FOMO tokens, which are used to create the liquidity pool. This process creates deflationary pressure for FOMO and the entire agent ecosystem. When creating your agent and token, you will have the option to pair your launch with FOMO or SOL, as our goal is not to alienate any project, but rather invite the best communities, CTO’s and builders to launch with us. If you decide to pair your project with FOMO you in turn get full marketing and dev support, once your project graduates the bonding curve and reaches Raydium. Further, as an added incentive, as our revenue grows we will be using part of the funds to support projects that have paired in FOMO. And Devs who launch tokens paired in FOMO will earn fees from their AI Agent token launch. Building the most robust agents using our framework will catapult us as one of the most prominent standards of the Solana ecosystem. Not only have we developed our own core infrastructure, but we also pull from some of the best repo’s and developer talent in all of AI, not just blockchain. Our team is comprised of 9 world class artificial intelligence engineers, PHDs in mathematics and engineering from the top companies on the cutting edge of AI. The future of AI Agents will be on Solana and we will help lead the way.

FOMO

129,867 views • 1 year ago

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

437,740 views • 4 months ago

The world of tomorrow cannot run on a rented cloud. 🚫 With 10 billion humans and 10 billion autonomous agents, intelligence must be embedded at the edge - not centralized in a server farm. The QVAC SDK is the invisible engine for this transition. We’ve built the foundational toolkit for the next era: highly efficient, fully modular, and 100% sovereign. From a single light to an industrial grid, the power to build local-first AI is now in your hands. The revolution will not be hosted. It will be local. Learn more:

The world of tomorrow cannot run on a rented cloud. 🚫 With 10 billion humans and 10 billion autonomous agents, intelligence must be embedded at the edge - not centralized in a server farm. The QVAC SDK is the invisible engine for this transition. We’ve built the foundational toolkit for the next era: highly efficient, fully modular, and 100% sovereign. From a single light to an industrial grid, the power to build local-first AI is now in your hands. The revolution will not be hosted. It will be local. Learn more:

QVAC

2,908,291 views • 2 months ago

We are building autonomous scientific discovery. And it runs 370x faster than a human scientist. Our AI agents index millions of scientific publications and learn what an entire field has done in the time it takes a researcher to read one paper. Then we bring it to the lab to verify and further fuel learnings. 10 years to discover a material? Not here.

We are building autonomous scientific discovery. And it runs 370x faster than a human scientist. Our AI agents index millions of scientific publications and learn what an entire field has done in the time it takes a researcher to read one paper. Then we bring it to the lab to verify and further fuel learnings. 10 years to discover a material? Not here.

Radical AI

85,389 views • 4 months ago

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.

Aaron Levie

91,863 views • 10 months ago

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!

Avi Chawla

138,735 views • 4 months ago

Kick back and earn. Build and make it rain. Agents are coming soon! Your agents automate yield, lending, and execution across chains — proposing every action for your approval while your funds remain in your control. And here’s the kicker: Beacon isn’t a closed system. We´re building agent infrastructure. You will be able to deploy or connect any agent from any chain, fully permissionless. A new layer of autonomous AI for DeFi in the making, built for users, builders, and protocols alike.

Kick back and earn. Build and make it rain. Agents are coming soon! Your agents automate yield, lending, and execution across chains — proposing every action for your approval while your funds remain in your control. And here’s the kicker: Beacon isn’t a closed system. We´re building agent infrastructure. You will be able to deploy or connect any agent from any chain, fully permissionless. A new layer of autonomous AI for DeFi in the making, built for users, builders, and protocols alike.

Beacon

544,529 views • 9 months ago

World’s 1st human-trained AI agent from visual data. iAgent leverages decentralized GPU infrastructure to turn gaming skills into valuable digital assets, enabling scalable AI training. Your Skill. Your Asset. Your iAgent. Own and monetize AI-powered agents, building your digital empire. Web3 and AI combined – the future of gaming and beyond. AI agents are set to scale globally across industries, and iAgent is leading the way in AI and gaming. Led by Jamie* GodJira_gangz, a Web3 veteran with a proven track record and backed by top investors like Dingaling among others. And strategic partners include Gaimin, AethirCloud, Team Secret, and Node City. We're excited to offer the 42 community early access to one of the top AI projects in the space. Register now:

World’s 1st human-trained AI agent from visual data. iAgent leverages decentralized GPU infrastructure to turn gaming skills into valuable digital assets, enabling scalable AI training. Your Skill. Your Asset. Your iAgent. Own and monetize AI-powered agents, building your digital empire. Web3 and AI combined – the future of gaming and beyond. AI agents are set to scale globally across industries, and iAgent is leading the way in AI and gaming. Led by Jamie* GodJira_gangz, a Web3 veteran with a proven track record and backed by top investors like Dingaling among others. And strategic partners include Gaimin, AethirCloud, Team Secret, and Node City. We're excited to offer the 42 community early access to one of the top AI projects in the space. Register now:

Q42

20,262 views • 1 year ago

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 views • 1 year ago

Not every AI interaction is best served with a large frontier model. There is a long tail of trillion-token use cases, from tagging to search, best served by a sub-10b-parameter model that runs in milliseconds and costs many orders of magnitude less than the frontier. We built Freesolo Flash to make training loops like SFT and RL easy and end-to-end completable through your coding agent.

Not every AI interaction is best served with a large frontier model. There is a long tail of trillion-token use cases, from tagging to search, best served by a sub-10b-parameter model that runs in milliseconds and costs many orders of magnitude less than the frontier. We built Freesolo Flash to make training loops like SFT and RL easy and end-to-end completable through your coding agent.

Freesolo

27,347 views • 16 days ago

The March to Mainnet is in full swing. ⚡️ This week, Co-Founder and Head of Research Neurmal//Theoriq takes us inside the latest from the research and engineering teams. He kicks things off with a look at the core agents powering AlphaSwarm—then dives into our first live deployment: a Knowledge Agent built and configured to Kaito AI 🌊 🌊 Think of Knowledge Agents as the swarm’s research desk, blending curated insight and real-time data to answer complex token, protocol & metric queries. Check out how these agents are being built, and the role they’ll play in Alpha Protocol and the Agentic future. 👇

The March to Mainnet is in full swing. ⚡️ This week, Co-Founder and Head of Research Neurmal//Theoriq takes us inside the latest from the research and engineering teams. He kicks things off with a look at the core agents powering AlphaSwarm—then dives into our first live deployment: a Knowledge Agent built and configured to Kaito AI 🌊 🌊 Think of Knowledge Agents as the swarm’s research desk, blending curated insight and real-time data to answer complex token, protocol & metric queries. Check out how these agents are being built, and the role they’ll play in Alpha Protocol and the Agentic future. 👇

Theoriq

26,611 views • 1 year ago

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

Andrew Ng

186,031 views • 1 year ago