|
RL at 1T Scale: prime-rl Performance Deep Dive
|
Matej Sirovatka |
2026-06-21 |
2,292 |
--
|
|
Systematic Reward Hacking and Prime Sprints
|
Jessica Li |
2026-05-20 |
3,751 |
3
|
|
METAGENE-1: Metagenomic Foundation Model
|
Sami |
2025-01-06 |
623 |
--
|
|
INTELLECT-3: A 100B+ MoE trained with large-scale RL
|
Prime Intellect Team |
2025-11-26 |
1,316 |
2
|
|
INTELLECT-2 Release: The First 32B Parameter Model Trained Through Globally Distributed Reinforcement …
|
Prime Intellect Team |
2025-05-11 |
847 |
201
|
|
Introducing Lab: The Full-Stack Platform for Training your Own Models
|
Prime Intellect Team |
2026-02-10 |
1,660 |
1
|
|
Releasing Hosted Evaluations: Making benchmarking effortless
|
Florian Brand |
2026-05-28 |
964 |
--
|
|
Scaling Our Open-Source Environments Program
|
Johannes |
2025-10-27 |
623 |
--
|
|
PCCL - Prime Collective Communications Library
|
Mike |
2025-05-20 |
1,218 |
2
|
|
Post-Training Nemotron 3 on Lab
|
Prime Intellect Team |
2026-06-04 |
1,016 |
--
|
|
Environments Hub: A Community Hub To Scale RL To Open AGI
|
Prime Intellect Team |
2025-08-27 |
953 |
3
|
|
TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
|
Johannes |
2025-01-28 |
1,908 |
1
|
|
$130M Series A to Build the Open Superintelligence Stack
|
Prime Intellect Team |
2026-07-08 |
627 |
3
|
|
Prime Intellect Joins the NVIDIA Nemotron Coalition to Advance Open Frontier Models
|
Prime Intellect Team |
2026-06-04 |
565 |
--
|
|
$15M to Build The Open Superintelligence Stack
|
Johannes |
2025-02-28 |
354 |
--
|
|
SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces
|
Johannes |
2025-07-10 |
1,098 |
--
|
|
SYNTHETIC-2
|
Johannes |
2025-06-23 |
1,005 |
--
|
|
Launching FrontierSWE on the Environments Hub
|
Rajan Agarwal (Proximal) |
2026-04-16 |
757 |
--
|
|
renderers: Token-Level Templating for Agentic RL
|
Prime Intellect Team |
2026-05-12 |
3,305 |
--
|
|
Partnering with Browserbase to Train Browser and Computer Use Agents
|
Jessica |
2026-03-30 |
338 |
--
|
|
SYNTHETIC-1: Scaling Distributed Synthetic Data Generation for Verified Reasoning
|
Vincent |
2025-02-06 |
1,300 |
1
|
|
General Agent: A Self-Evolving, Synthetic Agent Environment
|
Mika |
2026-05-18 |
3,537 |
--
|
|
INTELLECT-2: The First Globally Distributed Reinforcement Learning Training of a 32B Parameter …
|
Vincent |
2025-04-15 |
1,708 |
--
|
|
Planetary-Scale Inference: Building a Distributed Inference Engine for the Public Internet
|
Johannes |
2025-04-28 |
8,856 |
4
|
|
Recursive Language Models: the paradigm of 2026
|
Sebastian |
2026-01-01 |
7,194 |
1
|
|
Leveraging NVIDIA to Build the Open Superintelligence Stack
|
Prime Intellect Team |
2026-03-16 |
1,221 |
--
|
|
True Agents Model the World
|
Prime Intellect Team |
2026-06-05 |
4,897 |
--
|
|
Distributed Training in the Inference-Time-Compute Paradigm
|
Johannes |
2025-01-21 |
2,015 |
2
|
|
SYNTHETIC-1 Release: Two Million Collaboratively Generated Reasoning Traces from Deepseek-R1
|
Johannes |
2025-02-20 |
1,029 |
--
|
|
Releasing Lab: the training platform for self-improving agents
|
Prime Intellect Team |
2026-05-07 |
839 |
--
|
|
prime-rl gets an Algorithms layer
|
Prime Intellect Team |
2026-07-05 |
1,493 |
--
|
|
verifiers v1: Decomposing Tasksets and Harnesses for Agentic RL & Evaluations
|
Prime Intellect Team |
2026-07-10 |
2,362 |
--
|
|
Scaling Agentic RL: 365,000+ Environments for SWE, Terminal, and Search
|
Prime Intellect Team |
2026-07-22 |
3,176 |
4
|
|
Prime Agent: A self-improving RLM agent
|
Prime Intellect Team |
2026-08-05 |
3,520 |
254
|
|
Multi-Agent Systems in PRIME-RL
|
Prime Intellect Team |
2026-08-07 |
1,559 |
--
|
|
Prime Flash MoE - Faster MoE Kernels optimized for Blackwell
|
Mario Sieg |
2026-08-13 |
7,067 |
--
|
|
Measuring Autonomous AI Research
|
Prime Intellect |
2026-08-14 |
7,229 |
1
|
|
Uncovering a universal offline sandbox escape
|
Prime Intellect Team |
2026-08-25 |
1,585 |
2
|
