Skip to content
trendoviz

Tag

open-weight model evaluation

1 published trend · vote, save or discuss any of them

  1. AI for BusinessEmerging7D: Insufficient history

    DaisyRose-27B: RadixArk's Agent Post-Training Recipe

    RadixArk says its DaisyRose-27B combines failure-driven task curation, asynchronous reinforcement learning, long-session summarization and disposable sandboxes to post-train an agent model. The Apache 2.0-licensed checkpoints are inspectable, but the benchmark and efficiency figures come from the developer and have not been independently validated.

    Published

    AI agents & automation
    50 out of 100
    7D
    +100%
    Signals
    1
    Indep. src
    1
    Confidence
    Unconfirmed