ResearchPrime Intellect·7d ago·3 min readSummaryListen 0:44
Learnings from Auditing Public EvaluationsPrime Intellect published findings from auditing public evaluations.
News Hub
What actually shipped in agent engineering, pulled from the labs, arXiv and Hacker News.
See who we follow39 articles
ResearchPrime Intellect·18d ago·3 min readSummaryListen 0:43
Prime Mega MoE: Fast Fused MoE Kernels for TrainingPrime Mega MoE provides fast fused kernels for mixture-of-experts model training.
ResearchPrime Intellect·39d ago·3 min readSummaryListen 0:51
Prime Inference: Fast, Reliable Serving for Frontier Open ModelsPrime Inference provides fast and reliable serving infrastructure for frontier open-source language models.
ResearchPrime Intellect·50d ago·3 min readSummaryListen 0:39
Prime Sandboxes: MicroVMs for Agentic RL Training at ScalePrime Sandboxes provides MicroVMs for scaling agentic reinforcement learning training.
ResearchPrime Intellect·74d ago·3 min readSummaryListen 0:51
GLM-5.2 RL weight transfer in 4 seconds using NIXL and ModelExpressGLM-5.2 RL weight transfer completed in 4 seconds using NIXL and ModelExpress.
ResearchPrime Intellect·89d ago·3 min readSummaryListen 0:47
Prime Flash MoE - Faster MoE Kernels optimized for BlackwellPrime Flash MoE provides faster mixture-of-experts kernels optimized for Blackwell GPUs.
ResearchPrime Intellect·95d ago·3 min readSummaryListen 0:38
Multi-Agent Systems in PRIME-RLMulti-agent systems implemented in PRIME-RL framework.
ResearchPrime Intellect·111d ago·3 min read
Scaling Agentic RL: 365,000+ Environments for SWE, Terminal, and SearchPrime Intellect scaled agentic reinforcement learning to 365,000 plus environments for software engineering, terminal, and search tasks.
ResearchPrime Intellect·123d ago·3 min read
verifiers v1: Decomposing Tasksets and Harnesses for Agentic RL & EvaluationsPrime Intellect released verifiers v1 for decomposing tasksets and harnesses in agentic reinforcement learning and evaluations.
ResearchPrime Intellect·159d ago·3 min read
Post-Training Nemotron 3 on LabPrime Intellect enabled post-training of NVIDIA Nemotron 3 models on Lab.
ResearchPrime Intellect·159d ago·3 min read
Prime Intellect Joins the NVIDIA Nemotron Coalition to Advance Open Frontier ModelsPrime Intellect joined NVIDIA's Nemotron Coalition to develop open frontier AI models.
ResearchPrime Intellect·166d ago·3 min read
Releasing Hosted Evaluations: Making benchmarking effortlessPrime Intellect released Hosted Evaluations for simplified benchmarking.
ResearchPrime Intellect·176d ago·3 min read
General Agent: A Self-Evolving, Synthetic Agent EnvironmentGeneral Agent is a self-evolving synthetic agent environment.
ResearchPrime Intellect·182d ago·3 min read
renderers: Token-Level Templating for Agentic RLRenderers provides token-level templating for agentic reinforcement learning.
ResearchPrime Intellect·187d ago·3 min read
Releasing Lab: the training platform for self-improving agentsLab is a training platform for self-improving agents.
IndustryPrime Intellect·208d ago·3 min read
Launching FrontierSWE on the Environments HubFrontierSWE launched on the Environments Hub.
ResearchPrime Intellect·225d ago·3 min read
Partnering with Browserbase to Train Browser and Computer Use AgentsPrime Intellect partners with Browserbase to train agents for browser and computer use tasks.
ResearchPrime Intellect·239d ago·3 min read
Leveraging NVIDIA to Build the Open Superintelligence StackTitle alone insufficient to summarize open superintelligence stack using NVIDIA.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.