Dom
@dominik_scherm
Followers
3K
Following
6K
Media
143
Statuses
1K
Kardashev accelerator @PrimeIntellect ● Founder Aurea Berlin ● Europe AI ecosystem
Berlin / Earth
Joined December 2018
Open-source AGI is coming🫡
1
5
131
> Train models end-to-end with RL in your own environment/application > RL facilitates building specialized models > RL is an infra challenge While all the big labs are doing everything they can to convince companies to build on their closed APIs/models, despite telling everyone
highly underrated video @srush_nlp on building Cursor Composer and their agentic RL infrastructure https://t.co/561Ljmzaxh
8
27
288
highly underrated video @srush_nlp on building Cursor Composer and their agentic RL infrastructure https://t.co/561Ljmzaxh
6
28
328
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 :)
8
25
206
Hosted evals are live on our Environment Hub 🫡 Run your fav model, no setup needed. And share your benchmarks.
7
10
77
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 :)
10
13
201
Will Brown is everywhere
4
1
166
Very excited for this one after getting a hands-on sneak peek 🫡
0
0
5
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 https://t.co/WmY5lfDvnR
primeintellect.ai
Today, we're scaling up our open-source environments program to become the global hub for open evals and RL environments.As part of this, we're committing hundreds of thousands of $ in grants and...
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
nanochat runs for less than $80 on prime. the training setup is honestly worth trying just for the learning experience and works out of the box - might add support for our multi-node clusters next
5
10
241
Our Inference API is live. Use it to evaluate environments on the Hub. + Simple `prime env eval` cmd + One endpoint for all models + 56 models and growing + Unified billing with compute + Viewer for rewards and rollouts + Share results on Hub
7
27
188
Nvidia x Prime Intellect: Open-Source Model Builders & Scaling Meetup October 23 · 5:30-8 PM · San Francisco Join us https://t.co/NczzX2gDMk
11
18
189
18 months ago, @karpathy set a challenge: "Can you take my 2h13m tokenizer video and translate [into] a book chapter". We've done it! It includes prose, code & key images. It's a great way to learn this key piece of how LLMs work. https://t.co/aSgsZz0VxO
fast.ai
A text and code version of Karpathy’s famous tokenizer video.
32
351
3K
we're building out automations for the environmentshub - basic environment testing is live on every push, hosted evaluations and custom script execution coming next
All environments on the Hub now have automated checks. Built like Github Actions, it allows you to ensure that others can install and use your environments without issues. Custom triggers and advanced workflows coming soon.
1
4
63