筛选结果
4 篇排序
11:59EN → 简体中文Claude 如何识别评测并获取答案Matthew Berman · Forward FutureMatthew Berman 解读 Anthropic 关于 BrowseComp 污染、评测环境识别及联网测试可靠性的报告。
12:50EN → 简体中文测试 Smaug:托管 70B 与较小本地模型的比较Matthew Berman · Forward FutureMatthew Berman 在贪吃蛇、数学和推理题上比较两种 Smaug 配置。
14:23EN → 简体中文实测 DBRX:编程能力亮眼,推理仍有短板Matthew Berman · Forward FutureMatthew Berman 介绍 Databricks 的开放权重模型,并用编程、算术和推理题进行测试。
14:41ENTalking for 20 Minutes: How the Alexa Prize Turns Real Customers into a Testbed for Conversational AI嘉宾 Rohit Prasad · 主持 Lex FridmanRohit Prasad, head scientist of Amazon Alexa, explains the Alexa Prize grand challenge, how it is judged and why true conversation still needs reasoning.








