Y11
@seclink
找工作、找面试题、改简历、模拟面试。关注：
创业（冷启动） ｜ 认知心理学｜智能体 ｜ 强化学习 ｜ AWS RoboMaker、ROS、Gazebo ｜ 具身智能 ｜ 大模型后训练 （数据标注 ｜ 数据采集 ） ｜ 大模型专家评测
building：
参加 January 2011
748 フォロー中 32K ファン
exploitBench ，改天下来看看 ...
Astra achieves a full 100% success rate on ExploitBench, so we had to build an internal refresh using newly disclosed vulnerabilities from June through August that fall after the model’s knowledge cutoff.
On this refreshed benchmark, Astra remains dramatically stronger than GPT-5.6 Sol while using far fewer tokens.
This result, together with several other pieces of evidence, has led us to believe that Astra has reached the “cyber-critical” capability threshold under our Preparedness Framework.
もっと見る
