正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

😈 Today, we introduce WebGym, the largest-to-date open-source RL environment for web agent training that contains 300k tasks and a rollout framework optimized specifically for web environments' rollout speed. We reveal the effects of essential scaling directions we observe with WebGym. 1/n

Jack Bai

1,277 subscribers

45,075 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Firecrawl

123,163 次观看 • 2 个月前

Introducing the Environments Hub RL environments are the key bottleneck to the next wave of AI progress, but big labs are locking them down We built a community platform for crowdsourcing open environments, so anyone can contribute to open-source AGI

Introducing the Environments Hub RL environments are the key bottleneck to the next wave of AI progress, but big labs are locking them down We built a community platform for crowdsourcing open environments, so anyone can contribute to open-source AGI

Prime Intellect

1,814,857 次观看 • 9 个月前

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at

Yuke Zhu

141,486 次观看 • 2 年前

The wait is over!🚀 We are now live with Pera Web Wallet! 🌍 The ultimate open-source web wallet for managing all your #Algorand accounts and connecting to #dApps on desktop, built for security and ease of use. 🔗 Learn more:

The wait is over!🚀 We are now live with Pera Web Wallet! 🌍 The ultimate open-source web wallet for managing all your #Algorand accounts and connecting to #dApps on desktop, built for security and ease of use. 🔗 Learn more:

pera.algo

97,168 次观看 • 3 年前

We raised $1.5m to launch the world’s first LLM built for developer tasks. Run OCR, web scraping, STT, and classification that you can rely on for any dev tasks. Available in Beta starting today!

We raised $1.5m to launch the world’s first LLM built for developer tasks. Run OCR, web scraping, STT, and classification that you can rely on for any dev tasks. Available in Beta starting today!

Yoeven

93,421 次观看 • 8 个月前

We've been using Cua-Bench internally—and with customers—for the last few months to evaluate every computer-use agent we deploy. Today it's open-source. 15 public tasks, 40 variations, adapters for OSWorld and Windows Agent Arena. One CLI, self-hostable.

We've been using Cua-Bench internally—and with customers—for the last few months to evaluate every computer-use agent we deploy. Today it's open-source. 15 public tasks, 40 variations, adapters for OSWorld and Windows Agent Arena. One CLI, self-hostable.

Cua

87,270 次观看 • 5 个月前

We introduce 🔥X-InstructBLIP🔥, a simple and effective scalable cross-modal framework to empower LLMs to handle tasks across modalities such as text, image, video, sound, and 3D. Web: ArXiv: Code:

We introduce 🔥X-InstructBLIP🔥, a simple and effective scalable cross-modal framework to empower LLMs to handle tasks across modalities such as text, image, video, sound, and 3D. Web: ArXiv: Code:

Caiming Xiong

37,476 次观看 • 2 年前

Flow matters Practices go from instructional to open environments Today we went drills that emphasize context of COD to open reactive environments #football #strengthandconditioning #workout #lift #training #lifting #speed #strengthtraining #sprint #play #agility

Flow matters Practices go from instructional to open environments Today we went drills that emphasize context of COD to open reactive environments #football #strengthandconditioning #workout #lift #training #lifting #speed #strengthtraining #sprint #play #agility

Joseph Guarascio

129,841 次观看 • 1 年前

.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 次观看 • 3 个月前

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

430,406 次观看 • 3 个月前

we are starting our rollout of ChatGPT plugins. you can install plugins to help with a wide variety of tasks. we are excited to see what developers create!

we are starting our rollout of ChatGPT plugins. you can install plugins to help with a wide variety of tasks. we are excited to see what developers create!

Sam Altman

11,302,209 次观看 • 3 年前

🚀 Introducing Magentic-UI — an experimental human-centered web agent from Microsoft Research . It automates your web tasks while keeping you in control 🧠🤝—through co-planning, co-tasking, action guards, and plan learning. 🔓 Fully open-source. We can't wait for you to try it. 🔗

🚀 Introducing Magentic-UI — an experimental human-centered web agent from Microsoft Research . It automates your web tasks while keeping you in control 🧠🤝—through co-planning, co-tasking, action guards, and plan learning. 🔓 Fully open-source. We can't wait for you to try it. 🔗

AutoGen

38,409 次观看 • 1 年前

INTELLIGENT TASKS ARE A STEPPING STONE TO AGI Today, we are launching ChatLLM Tasks. We have hooked up tools like web search, email, and web scrappers to mini-agents that can be triggered on a schedule. These tasks combine intelligent tool use with crons! We think this is the first step towards AGI. The next step is to connect our AI engineer to create more complex tasks. AGI STEP ONE - DONE!

INTELLIGENT TASKS ARE A STEPPING STONE TO AGI Today, we are launching ChatLLM Tasks. We have hooked up tools like web search, email, and web scrappers to mini-agents that can be triggered on a schedule. These tasks combine intelligent tool use with crons! We think this is the first step towards AGI. The next step is to connect our AI engineer to create more complex tasks. AGI STEP ONE - DONE!

Bindu Reddy

18,486 次观看 • 1 年前

PlayCanvas Engine v2.13.0 is here 🚀 Your free and open source 3D engine for the web ✅ Streamed LOD system for 3D Gaussian Splats ✅ Splat shader effects framework ✅ Globally sorted splats [1 / 2]

PlayCanvas Engine v2.13.0 is here 🚀 Your free and open source 3D engine for the web ✅ Streamed LOD system for 3D Gaussian Splats ✅ Splat shader effects framework ✅ Globally sorted splats [1 / 2]

PlayCanvas

37,210 次观看 • 7 个月前

We are excited to introduce the Text to Sound Effects API. To showcase it - we've built the first Video to Sounds Effects app. This app is available for free online and fully open-source.

We are excited to introduce the Text to Sound Effects API. To showcase it - we've built the first Video to Sounds Effects app. This app is available for free online and fully open-source.

ElevenLabs

120,703 次观看 • 2 年前

🔥Excited to share our new work: "A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning"! We systematically study what actually works (and what doesn't) for agentic multi-turn RL, breaking down the design space into 3 pillars: 🌎Environment, 🤖Policy, and ⭐Reward. We conduct various ablations and empirical analysis on 🧩TextWorld, 🧙ALFWorld, and 🧑‍💻SWE-Gym. We also open source our codebase: 🐈🍵Meow-Tea-Taro 💜, a modular multi-turn RL framework with configurable environments, policies, and rewards! #ReinforcementLearning #AgenticAI #LLMs #Agents

🔥Excited to share our new work: "A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning"! We systematically study what actually works (and what doesn't) for agentic multi-turn RL, breaking down the design space into 3 pillars: 🌎Environment, 🤖Policy, and ⭐Reward. We conduct various ablations and empirical analysis on 🧩TextWorld, 🧙ALFWorld, and 🧑‍💻SWE-Gym. We also open source our codebase: 🐈🍵Meow-Tea-Taro 💜, a modular multi-turn RL framework with configurable environments, policies, and rewards! #ReinforcementLearning #AgenticAI #LLMs #Agents

Ruiyi Wang 王睿仪

52,924 次观看 • 8 个月前

We’re launching Mundi, the first open-source web GIS built for AI. After years of training geospatial AI models, we decided now is the moment to build the GIS software of the next decade. After the AI Vectorizer, Georeferencer, and Kue (our LLM agent inside QGIS), we realized that GIS is at an inflection point. But existing mapping software was neither powerful enough to allow for synchronous collaboration with AI agents, nor open source to allow the community to build on top of it. If we want to get the most out of LLMs, we need to create our own GIS that is purposefully designed for AI—Mundi. With Mundi, you collaborate with Kue, our AI GIS agent, to edit your map, rather than physically interacting with tools as you would in a legacy GIS.

We’re launching Mundi, the first open-source web GIS built for AI. After years of training geospatial AI models, we decided now is the moment to build the GIS software of the next decade. After the AI Vectorizer, Georeferencer, and Kue (our LLM agent inside QGIS), we realized that GIS is at an inflection point. But existing mapping software was neither powerful enough to allow for synchronous collaboration with AI agents, nor open source to allow the community to build on top of it. If we want to get the most out of LLMs, we need to create our own GIS that is purposefully designed for AI—Mundi. With Mundi, you collaborate with Kue, our AI GIS agent, to edit your map, rather than physically interacting with tools as you would in a legacy GIS.

Brendan Ashworth

41,011 次观看 • 1 年前

Yesterday we announced a builder side quest, asking for web apps that showcased the 10x speed of Flashblocks We got so many great submissions that we increased the prize pool from 2 to 3 ETH, and announced the 6 finalists live at ETHDenver:

Yesterday we announced a builder side quest, asking for web apps that showcased the 10x speed of Flashblocks We got so many great submissions that we increased the prize pool from 2 to 3 ETH, and announced the 6 finalists live at ETHDenver:

Base Build

52,239 次观看 • 1 年前

We asked Mika Senghaas how RL environments need to change for better agents. His take: stop treating environments like static snapshots. Today, researchers manually define tasks and rewards. Prime Intellect is working toward a loop where agents solve tasks and help create harder ones. “Up to now, environments are still these static snapshots. The task in and of itself is sort of hard-coded.” “What gets really interesting is once we can fully close the loop.” “The policy you’re training is not only a solver... it also becomes an instance creating new tasks on the fly.”

We asked Mika Senghaas how RL environments need to change for better agents. His take: stop treating environments like static snapshots. Today, researchers manually define tasks and rewards. Prime Intellect is working toward a loop where agents solve tasks and help create harder ones. “Up to now, environments are still these static snapshots. The task in and of itself is sort of hard-coded.” “What gets really interesting is once we can fully close the loop.” “The policy you’re training is not only a solver... it also becomes an instance creating new tasks on the fly.”

MTS

15,324 次观看 • 1 个月前