Skip to content
AX AI Daily
中EN
Trending storyDeveloping

OpenAI publishes GPT-Rosalind-6 system card addendum

1 report1 sourceupdated 3 hours ago

What happened

AI digest

On November 2, Hacker News' front page covered OpenAI's GPT-Rosalind-6 system card addendum, covering biological capability evaluations and access controls. The report says GPT-Rosalind-6 uses the same weights as GPT-6 Astra, with no added training data or extra post-training for this release. At the highest tested reasoning budget on GeneBench Pro v13, GPT-Rosalind-6 and GPT-Rosalind-5.5 had single-attempt success rates of 37.7% and 16.7%. The report notes this evaluation setup differs from production.

Written by AI from the coverage · updated 1 hour ago

LatestNov 2 22:44
The addendum discloses the model's weights and training, plus biological capability results under a non-production setup.

Coverage

Follow the reports to see the story from different sides.

Nov 2
  1. Hacker News front page
    GPT-Rosalind-6 System Card Addendum

    OpenAI 的 GPT-Rosalind-6 系统卡补充报告披露，该模型与 GPT-6 Astra 使用相同权重，此次发布未增加训练数据或进行额外后训练。GeneBench Pro v13 的最高受测推理预算下，GPT-Rosalind-6 与 GPT-Rosalind-5.5 的单次成功率分别为 37.7% 和 16.7%，评测配置不同于生产环境。

Heat over time

Not enough continuous observations to draw a trend yet.