All tags

Model: "gpt-3"

    QwQ-32B claims to match DeepSeek R1-671B
    o3 solves AIME, GPQA, Codeforces, makes 11 years of progress in ARC-AGI and 25% in FrontierMath
    Mamba-2: State Space Duality
    Contextual Position Encoding (CoPE)
    Life after DPO (RewardBench)
    12/12/2023: Towards LangChain 0.1