Video wird geladen...

Video konnte nicht geladen werden

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

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

84,286 subscribers

1,818,549 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Nachrichten & Politik Bildung

Anya Rossi• Live Now

Private livecam show

42 Kommentare

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

Environments are where agents learn. They define the world, rules, and feedback loop of state → action → reward. Everything from coding/math tasks to games and multi-turn dialogue evals can be thought of as environments. Without them, RL is just math with nothing to interact with.

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

This is why environments are pivotal to the next wave of AI progress. But while big labs are spending millions buying and privatizing RL environments, open-source has no comparable way to crowd-source them at scale. We’re building the platform and infrastructure to change that.

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

The Environments Hub is an open, community-powered platform to create, explore, and reuse environments. Lowering the barrier for anyone to contribute to state-of-the-art RL.

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

Key features: - Pull, push & manage environments via Hub or CLI - Generate evaluation reports across models - Deep integration with verifiers framework - Native environments support in our prime-rl trainer - Native sandbox support for code execution

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

In last week’s private beta, over 30 researchers and companies contributed environments to the Hub. Special shoutout to @arcee_ai, @hud_evals, @WhyPhy_Labs, @GroqInc, and the many individuals who contributed their first environments to the hub!

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

We’re also opening up a list of RFCs and bounties for new environments. These tasks are intentional: collectively building towards INTELLECT-3, a fully open, agentic, state-of-the-art model.

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

Next Steps: Providing The Full-Stack Open AGI Infrastructure - Crowd-source RL environments at scale - Train a fully open agentic SOTA model with INTELLECT-3 - Seamlessly integrate an ecosystem of tools, sandboxes, RFT, and inference - Provide the open AI infrastructure stack rivaling what’s behind the walls of closed labs

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

Links - - - - - -

Profilbild von Prime Intellect

Prime Intellectvor 1 Jahr

Read more

Profilbild von will brown

will brownvor 1 Jahr

🚀🚀🚀

Profilbild von Lucas Beyer (bl16)

Lucas Beyer (bl16)vor 1 Jahr

Congrats, let the environments prosper!

Profilbild von Sam Hogan 🇺🇸

Sam Hogan 🇺🇸vor 1 Jahr

Not sure what this is but I’m proud of you guys

Profilbild von kache

kachevor 1 Jahr

HOLY MOLY

Profilbild von ludwig

ludwigvor 1 Jahr

sick

Profilbild von stochasm

stochasmvor 1 Jahr

Let's go

Profilbild von Ishan Goswami

Ishan Goswamivor 1 Jahr

You should have @ExaAILabs as a web search tool

Profilbild von elie

elievor 1 Jahr

lfg!! congrats 🤗

Profilbild von naklecha

naklechavor 1 Jahr

very cool!!!

Profilbild von himanshu

himanshuvor 1 Jahr

github for rl is here, crazy ship⚡

Profilbild von Hensen Juang

Hensen Juangvor 1 Jahr

Congrats

Florian Brandvor 1 Jahr

🚀🫡

Profilbild von Zach Mueller

Zach Muellervor 1 Jahr

Congrats team!

Profilbild von Lazarz

Lazarzvor 1 Jahr

Music? (Sick)

Profilbild von dcbuilder.eth ⚪️

dcbuilder.eth ⚪️vor 1 Jahr

unfathomably based

Profilbild von Prince Canuma

Prince Canumavor 1 Jahr

Awesome!

Profilbild von Jody Hirschi 🍫

Jody Hirschi 🍫vor 1 Jahr

Are y'all utilizing puffer to make these envs fast?

Profilbild von bigray0x.eth ⚡️

bigray0x.eth ⚡️vor 1 Jahr

👀

Profilbild von gustofied

gustofiedvor 1 Jahr

a prediction market for this and the market/people will fund any new agent. need to find the reward structure on that, would it be company who wants a specific agent, or would it be embedded into the agent's internals, some staking form.

Profilbild von Alex Veremeyenko

Alex Veremeyenkovor 1 Jahr

the environments hub is a game-changer, opens up so many possibilities for research and innovation. excited to see how this evolves and the contributions that come in.

Profilbild von VV

VVvor 1 Jahr

🔥🔥🔥

Profilbild von djcows

djcowsvor 1 Jahr

this is a good direction

Profilbild von parth

parthvor 1 Jahr

hell yeah! congrats guys!!

Profilbild von Uncertain Systems (e/acc)

Uncertain Systems (e/acc)vor 1 Jahr

I hate living in Europe rn

Profilbild von Dhruv

Dhruvvor 1 Jahr

this looks gooood!

Profilbild von Emily

Emilyvor 1 Jahr

Thank you for all the fantastic work 🙏

Profilbild von Uday Bhaskar

Uday Bhaskarvor 1 Jahr

This is amazing, congratulations!

Profilbild von λux

λuxvor 1 Jahr

LFG⚡️huge congrats to the team

Profilbild von Taha Yassine 🍉

Taha Yassine 🍉vor 1 Jahr

Huge! congrats

Profilbild von EDITH

EDITHvor 1 Jahr

🔥🔥🔥

Profilbild von Zhi Rui Tam

Zhi Rui Tamvor 1 Jahr

Maybe try porting these first:

Profilbild von Taste

Tastevor 1 Jahr

open sourcing rl environments is exactly the push ai needs right now

Profilbild von Superchillen eth/acc

Superchillen eth/accvor 1 Jahr

That’s based

Ähnliche Videos

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Base Labs

228,804 Aufrufe • vor 10 Tagen

TRADING HIGH-VOLATILITY ENVIRONMENTS High-volatility environments are the ones we live for. That is when we size up aggressively & make all of our big money, right? That is the mindset of many traders & I think they're missing this key concept which leads to so many blowups.

TRADING HIGH-VOLATILITY ENVIRONMENTS High-volatility environments are the ones we live for. That is when we size up aggressively & make all of our big money, right? That is the mindset of many traders & I think they're missing this key concept which leads to so many blowups.

Lance Breitstein 🇺🇸🌎

47,325 Aufrufe • vor 1 Jahr

1 million tech jobs are at risk of going overseas. As the U.S. goes down a path of regulatory uncertainty, the EU, UK, UAE, Hong Kong, Singapore, Australia, and Japan are all creating environments for crypto to flourish so that they can capitalize on the next wave of innovation.

1 million tech jobs are at risk of going overseas. As the U.S. goes down a path of regulatory uncertainty, the EU, UK, UAE, Hong Kong, Singapore, Australia, and Japan are all creating environments for crypto to flourish so that they can capitalize on the next wave of innovation.

Coinbase 🛡️

1,788,022 Aufrufe • vor 3 Jahren

hillclimb (hillclimb) is the human superintelligence community, dedicated to building golden datasets for AGI. Starting with math, their team of IMO medalists, lean experts, PhDs is designing RL environments for Nous Research.

hillclimb (hillclimb) is the human superintelligence community, dedicated to building golden datasets for AGI. Starting with math, their team of IMO medalists, lean experts, PhDs is designing RL environments for Nous Research.

Y Combinator

911,390 Aufrufe • vor 10 Monaten

😈 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

😈 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

45,147 Aufrufe • vor 8 Monaten

We're introducing EnvHub to LeRobot! Upload simulation environments to the @hugginigface hub, and load them in lerobot, with one line of code ! env = lerobot.make_env("username/my-env", trust_remote_code=True) Back in 2017, OpenAI called on the community to build Gym environments. Today, we're doing the same for robotics. We're calling researchers, students, hobbyists, labs, and startups to publish complex envs, tasks, and benchmarks on the Hub, so we see how robot policies perform. (in Isaaac, Mujoco, Genesis, etc..) Fill out and submit the form linked in the comments to join the effort!

We're introducing EnvHub to LeRobot! Upload simulation environments to the @hugginigface hub, and load them in lerobot, with one line of code ! env = lerobot.make_env("username/my-env", trust_remote_code=True) Back in 2017, OpenAI called on the community to build Gym environments. Today, we're doing the same for robotics. We're calling researchers, students, hobbyists, labs, and startups to publish complex envs, tasks, and benchmarks on the Hub, so we see how robot policies perform. (in Isaaac, Mujoco, Genesis, etc..) Fill out and submit the form linked in the comments to join the effort!

jade

43,296 Aufrufe • vor 10 Monaten

Today I’m excited to introduce micro1 Intelligence, the world’s most advanced platform for training frontier AI models. Achieving AGI is bottlenecked by one main thing: high-quality data. Data based on real-world environments that capture human expert workflows, complex decision-making, and reward signals models need to learn. With micro1 Intelligence, frontier labs can train on RL environments across every subject matter all in one place.

Today I’m excited to introduce micro1 Intelligence, the world’s most advanced platform for training frontier AI models. Achieving AGI is bottlenecked by one main thing: high-quality data. Data based on real-world environments that capture human expert workflows, complex decision-making, and reward signals models need to learn. With micro1 Intelligence, frontier labs can train on RL environments across every subject matter all in one place.

Ali Ansari

333,129 Aufrufe • vor 9 Monaten

"So, in the body, we can create an environment that's very hospitable for cancer. We can create an environment that's very inhospitable to cancer. Number one, it has few areas of fungal hypoxia—it has few areas of the body that are deprived of oxygen. Healthy circulation and movement, sunlight, things like red light therapy. The second thing is we don’t have an environment that is very acidic. We know that alkaline environments tend to be disease-free environments. Acidic environments tend to be disease-prone environments." Gary Brecka

"So, in the body, we can create an environment that's very hospitable for cancer. We can create an environment that's very inhospitable to cancer. Number one, it has few areas of fungal hypoxia—it has few areas of the body that are deprived of oxygen. Healthy circulation and movement, sunlight, things like red light therapy. The second thing is we don’t have an environment that is very acidic. We know that alkaline environments tend to be disease-free environments. Acidic environments tend to be disease-prone environments." Gary Brecka

Shawn Ryan

272,985 Aufrufe • vor 1 Jahr

Open-source VLA from Galaxea Dynamics shown on a wide range of environments and with different objects, and all running on their cheap off the shelf hardware. Really great contribution to the community.

Open-source VLA from Galaxea Dynamics shown on a wide range of environments and with different objects, and all running on their cheap off the shelf hardware. Really great contribution to the community.

Chris Paxton

30,133 Aufrufe • vor 8 Monaten

This Indian Developer made 41.7 Lakh in roughly 2 months. He builds RL environments for AI labs. Here’s what that actually means. You don’t write answers for the AI. You set its exam. Take a real GitHub repo with a real bug. Pin it inside Docker so it runs identically every time. Write the task. Write a grader that returns an automatic pass or fail. Write your own gold solution to prove it’s solvable. Then make sure the model can’t cheat its way to a pass. The labs have run out of internet data. This is the next lever. Anthropic reportedly discussed spending over $1B on this in a single year. Where to start: Prime Intellect’s Environments Hub is free to enter and has 2,500+ open environments. Ship one as a public PR. Then apply to Mercor, Surge or Handshake with that PR as proof. Week 1 he made ₹6,880. Start. Comment “RL” for the full breakdown and link to Whatsapp Channel in the bio! #ai #rl #hiring #google

This Indian Developer made 41.7 Lakh in roughly 2 months. He builds RL environments for AI labs. Here’s what that actually means. You don’t write answers for the AI. You set its exam. Take a real GitHub repo with a real bug. Pin it inside Docker so it runs identically every time. Write the task. Write a grader that returns an automatic pass or fail. Write your own gold solution to prove it’s solvable. Then make sure the model can’t cheat its way to a pass. The labs have run out of internet data. This is the next lever. Anthropic reportedly discussed spending over $1B on this in a single year. Where to start: Prime Intellect’s Environments Hub is free to enter and has 2,500+ open environments. Ship one as a public PR. Then apply to Mercor, Surge or Handshake with that PR as proof. Week 1 he made ₹6,880. Start. Comment “RL” for the full breakdown and link to Whatsapp Channel in the bio! #ai #rl #hiring #google

Arsh Goyal

38,423 Aufrufe • vor 20 Tagen

Introducing Zeroth-01 Bot: the world's smallest open-source end-to-end humanoid robot starting at $350! Fully open-source, including hardware, SDK, sim environments & more. Zeroth-01 is the most hackable humanoid to-date! Join⬇️to shape the future of accessible robotics w/ us

Introducing Zeroth-01 Bot: the world's smallest open-source end-to-end humanoid robot starting at $350! Fully open-source, including hardware, SDK, sim environments & more. Zeroth-01 is the most hackable humanoid to-date! Join⬇️to shape the future of accessible robotics w/ us

JX

143,904 Aufrufe • vor 1 Jahr

Hiring RL Engineer! Started off as a curious project at Lossfunk to push the boundaries of LLMs in social reasoning - we are now building RL environments, data, and benchmarks to simulate more real-world scenarios. If you want to train SoTA RL models over multi-GPUs (H200s/B200s) to unlock next AI frontier, this is for you.

Hiring RL Engineer! Started off as a curious project at Lossfunk to push the boundaries of LLMs in social reasoning - we are now building RL environments, data, and benchmarks to simulate more real-world scenarios. If you want to train SoTA RL models over multi-GPUs (H200s/B200s) to unlock next AI frontier, this is for you.

Satpal Singh Rathore

46,010 Aufrufe • vor 1 Jahr

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more

Prime Intellect

1,150,419 Aufrufe • vor 9 Monaten

During the development of Spark, we built a demo to showcase the potential of using full scale AI generated 3D worlds as immersive VR environments.

During the development of Spark, we built a demo to showcase the potential of using full scale AI generated 3D worlds as immersive VR environments.

spark

84,725 Aufrufe • vor 1 Jahr

Introducing Agent Baseline: a vendor-neutral reference architecture for safely building, deploying, and operating AI agents in enterprise environments. Created with Snyk and Keycard, this open-source framework sets the minimum standard for agent safety:

Introducing Agent Baseline: a vendor-neutral reference architecture for safely building, deploying, and operating AI agents in enterprise environments. Created with Snyk and Keycard, this open-source framework sets the minimum standard for agent safety:

Docker

18,594 Aufrufe • vor 1 Monat

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Google AI

102,711 Aufrufe • vor 1 Jahr

Today we are introducing 2 key features to JAIGP: AI Review & Open Prompting. AI review is part of 5-step process where papers get feedback from & are evaluated based on their ability to address that feedback. This means they are not stuck in an endless AI review loop. Open prompting is a newer idea. We are making all prompts we used to create JAIGP open, and also, opening up the journal's rules to the community for suggestions. You can suggest the prompt we should run next! So, if you have opinions about AI generated papers, you can share them directly with us at

Today we are introducing 2 key features to JAIGP: AI Review & Open Prompting. AI review is part of 5-step process where papers get feedback from & are evaluated based on their ability to address that feedback. This means they are not stuck in an endless AI review loop. Open prompting is a newer idea. We are making all prompts we used to create JAIGP open, and also, opening up the journal's rules to the community for suggestions. You can suggest the prompt we should run next! So, if you have opinions about AI generated papers, you can share them directly with us at

César A. Hidalgo

13,453 Aufrufe • vor 5 Monaten

Ryan believes we could get 3-6 years of AI progress at the current pace, but in a single year, once we automated AI R&D. So a jump as big as GPT 3.5 to Mythos in a single year. A big crux is whether you'd end up bottlenecked by data. It seems to that a big source of AI progress currently is human expert data, codified into RL environments and SFT data. Ryan doesn't think human expert data is a primary driver of AI progress, and this ended up being a fruitful debate during the conversation.

Ryan believes we could get 3-6 years of AI progress at the current pace, but in a single year, once we automated AI R&D. So a jump as big as GPT 3.5 to Mythos in a single year. A big crux is whether you'd end up bottlenecked by data. It seems to that a big source of AI progress currently is human expert data, codified into RL environments and SFT data. Ryan doesn't think human expert data is a primary driver of AI progress, and this ended up being a fruitful debate during the conversation.

Dwarkesh Patel

93,931 Aufrufe • vor 1 Monat

Reinforcement learning research often depends on static benchmarks and obscure leaderboards. But real evaluation happens inside environments, with specific tools, prompts, constraints, and workflows. Today, we’re launching the Turing RL Environments Evaluation Platform. Researchers now have direct, real time access to: -The exact production RL environments used in evaluation -Full tool inventories and prompt transparency -Explicit QA rubrics and scoring criteria -Live, harness-integrated leaderboards -Interactive demos of agent workflows No abstractions. No summarized results. Just the system itself. Explore the platform below.

Reinforcement learning research often depends on static benchmarks and obscure leaderboards. But real evaluation happens inside environments, with specific tools, prompts, constraints, and workflows. Today, we’re launching the Turing RL Environments Evaluation Platform. Researchers now have direct, real time access to: -The exact production RL environments used in evaluation -Full tool inventories and prompt transparency -Explicit QA rubrics and scoring criteria -Live, harness-integrated leaderboards -Interactive demos of agent workflows No abstractions. No summarized results. Just the system itself. Explore the platform below.

Turing

69,730 Aufrufe • vor 4 Monaten