Log inSign up
Prime Intellect profile banner
user avatar

Prime Intellect

@PrimeIntellect
Open Superintelligence Stack
primeintellect.ai
Joined June 2020
42
Following
82.9K
Followers
AffiliatesRepliesArticlesMedia
  • Pinned
    user avatar
    Prime Intellect
    @PrimeIntellect
    Aug 5
    Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.
    Image
    00:00
  • user avatar
    Prime Intellect
    @PrimeIntellect
    Aug 15
    We ran the largest open experiment on how frontier models do AI research. 100+ autonomous runs across 10+ models, sandboxed on 8xH200s for up to 8 days, iterating on the nanoGPT optimizer track. Best runs closed 82% of the gap to a record built by dozens of humans over months.
    Image
  • user avatar
    Prime Intellect
    @PrimeIntellect
    Aug 13
    The team at @mixedbreadai used Prime Intellect to train Toast 1. A state-of-the-art search agent that retrieves relevant documents, Slack messages, Drive files, PDFs, and images. The resulting model matches GPT-5.6 Sol and Opus 5 while being up to 12x faster and 10x cheaper.
    Image
    Image
    01:08
    user avatar
    Mixedbread
    @mixedbreadai
    Aug 13
    Introducing Toast 1, our first specialised search agent. Toast 1 sets a new Pareto frontier for agentic search models. Frontier search quality, across all domains, 12x faster, at 1/10th of the price.
  • user avatar
    Prime Intellect
    @PrimeIntellect
    Aug 11
    Nemotron 3.5 Lightning is here, with Day-0 support on Prime Intellect 30B MoE with 3B active params, up to 4x higher throughput, 30% faster task completion Post-train it for your own domain with prime-rl and Prime Lab primeintellect.ai
    Image
    Image
    user avatar
    NVIDIA AI
    NVIDIA
    @NVIDIAAI
    Aug 11
    Introducing NVIDIA Nemotron 3.5 Lightning⚡ An open 30B MoE model with 3B active parameters, built for always-on agents to complete high-volume, specialized tasks faster. It delivers up to 4x the output speed of similar-sized models.