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 retweeted
RL LEARNING WITH LORA: A DIVERSE DEEP DIVE
Prime Intellect retweeted
verifiers v0.1.7 is released 🚀 this one's all about making RL training and experimentation waaaay easier: - single-command installation for prime-rl - single-command training w/ unified configs - overhauled vf.RLTrainer for hacking on new algorithms quick demo + links below :)
Prime Intellect retweeted
Hosted Evaluations are Live Evaluate environments directly on our platform, without needing a CLI
Prime Intellect retweeted
The Environment Hub now supports evals - any RL environment can be evaluated using the most popular models.
Hosted Evaluations are Live Evaluate environments directly on our platform, without needing a CLI
2
10
77
Prime Intellect retweeted
B200 deployment for the best payment network on earth @cloudwalk
3
71
Prime Intellect retweeted
the Environments Hub is also a full-service evals platform :) are you seeing the vision
Hosted evals are live on our Environment Hub 🫡 Run your fav model, no setup needed. And share your benchmarks.
9
8
2
123
Prime Intellect retweeted
Hosted evals are live on our Environment Hub 🫡 Run your fav model, no setup needed. And share your benchmarks.
Prime Intellect retweeted
you can just create environments
creating an environment with verifiers is as simple as writing a load_environment function and filling out a pyproject.toml, both of which are initialized for you when you do `prime env init` environments are packages, and can be used with prime-rl, skyrl, tinker, and more :)
1
7
66
Prime Intellect retweeted
creating an environment with verifiers is as simple as writing a load_environment function and filling out a pyproject.toml, both of which are initialized for you when you do `prime env init` environments are packages, and can be used with prime-rl, skyrl, tinker, and more :)
Prime Intellect retweeted
We're scaling our Open-Source Environments Program As part of this, we're committing hundreds of thousands of $ in bounties and looking for partners who want to join our mission to accelerate open superintelligence Join us in building the global hub for environments and evals
Prime Intellect retweeted
i'm spearheading a new team within @primeintellect called Applied Research. we span multiple efforts including verifiers, the Environments Hub, training + eval products, client engagements, and community growth. our job is to bring research infra to everybody. we're hiring.
Prime Intellect retweeted
contribute to open superintelligence $200k+ bounties to build open rl environments
We're scaling our Open-Source Environments Program As part of this, we're committing hundreds of thousands of $ in bounties and looking for partners who want to join our mission to accelerate open superintelligence Join us in building the global hub for environments and evals
Prime Intellect retweeted
if you or a loved one is looking to learn about building environments and get a bag in the process, inquire within our bounty list is bigger and better than ever
We're scaling our Open-Source Environments Program As part of this, we're committing hundreds of thousands of $ in bounties and looking for partners who want to join our mission to accelerate open superintelligence Join us in building the global hub for environments and evals
Prime Intellect retweeted
Today, we are scaling our OS environments program with a new wave of bounties live for - Flagship benchmarks - Evals for popular software tools - Automated AI research tasks - Integrations with RL trainers ⁃ Major features to Prime Intellect libraries primeintellect.ai/blog/scali…
We're scaling our Open-Source Environments Program As part of this, we're committing hundreds of thousands of $ in bounties and looking for partners who want to join our mission to accelerate open superintelligence Join us in building the global hub for environments and evals
4
12
110
Prime Intellect retweeted
I wish this existed when I started my ml journey. Open source has an incentive problem and we are hoping to create a broader ecosystem to fix it
We're scaling our Open-Source Environments Program As part of this, we're committing hundreds of thousands of $ in bounties and looking for partners who want to join our mission to accelerate open superintelligence Join us in building the global hub for environments and evals
8
5
123