Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Prime Intellect

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 3

  1. Prime Intellect and NVIDIA post-train Nemotron 3.5 Super VL for enterprise agents

    Prime Intellect and NVIDIA built a 2,500-task verified enterprise dataset and ran 100 GRPO steps (about 11 hours on 128 NVIDIA GB200 GPUs) to lift NVIDIA Nemotron 3.5 Super VL from 34.0% at its SFT checkpoint to 57.7% on the public split of AutomationBench-AA, a 23.7-point gain. The tasks span 47 simulated SaaS applications such as CRMs, inboxes, help desks and spreadsheets, and scoring inspects only the final application state: partial credit for objectives met, zeroed if any guardrail is violated. The post says every task is attacked with scripted shortcuts (blanket actions, doing nothing, claiming success) before admission, with about 18,000 attempts in the latest batches getting through none, and a second independent grader matching scores byte for byte on roughly 69,000 episodes.

    Prime Intellect Blog · 🔥 5
  2. Prime Intellect acquires Moondream, adds Moondream 3.1 and Photon to its inference stack

    Prime Intellect announced it has acquired Moondream, with founders Vik Korrapati and Jay Allen joining to lead and scale inference and to accelerate multimodal work spanning vision and computer use. Moondream 3.1 is now available through Prime Inference powered by Moondream's Photon engine, and Photon plus Moondream's GPU kernel and megakernel compiler work are being integrated into Prime's stack. Clef and Clef Flash are also live through Prime Inference and OpenRouter, with Clef priced at parity with Jev and Clef Flash at half the price; existing Moondream Cloud customers will receive platform credits in the coming days.

    Prime Intellect Blog · 🔥 0
  3. Prime Agent rewritten in Rust by a 2,000-agent swarm

    Prime Intellect shipped a from-scratch Rust rewrite of Prime Agent, its coding agent, which it says has been downloaded more than 300,000 times and processed over 8 trillion tokens since launching in August. Per the company's blog, the port took two weeks and was orchestrated by more than 2,000 agents across 10,000-plus Prime Sandboxes, consuming over 200 billion tokens from Prime Inference's GLM-5.3 endpoint; work was split into a topological ordering of tasks, with each task passing through a Planner, Implementer, Reviewer and Verifier, gated by TUI, harness, protocol and feature parity checks. A follow-up three-day hillclimbing loop logged 144 experiment and audit records and merged 69 changes, cutting cold-start input-ready latency from 736.1 ms in the TypeScript version to 51.9 ms (about 14.18x), 10 MiB session process memory from 1,130.0 MB to 237.3 MB, and install size from 172.1 MB to 59.6 MB.

    Prime Intellect Blog · 🔥 0

Experience and discussion from the community

Share my Prime Intellect experienceAsk about Prime Intellect

Nobody has shared their experience with Prime Intellect yet.