Older models were more prone to submitting prematurely, even when test cases weren't passing.
这一观察揭示了不同AI模型版本之间在任务坚持性上的显著差异。早期模型更容易过早提交不完整的解决方案，而最新模型表现出更强的任务坚持性和工程判断力。这种差异可能反映了AI在自我评估和任务管理能力上的进化。
6 Matching Annotations
- Last 7 days
-
-
-
www.microsoft.com www.microsoft.com
-
Performance on knowledge-heavy tasks depends strongly on model size and training, while reasoning-oriented models show clear gains on tasks requiring logic, learning, abstraction, and social inference.
令人惊讶的是：知识密集型任务的性能强烈依赖于模型规模和训练，而推理导向模型在需要逻辑、学习、抽象和社会推理的任务上显示出明显优势。这一发现揭示了不同AI模型在能力分布上的根本差异，为模型选择和优化提供了重要指导。
-
- Apr 2026
-
transformer-circuits.pub transformer-circuits.pub
-
we studied emotion-related representations in Claude Sonnet 4.5, a frontier LLM at the time of our investigation.
【启发】这篇论文只研究了 Claude Sonnet 4.5 一个模型，但它的方法论对所有大模型都适用。这启发了一个迫切的研究议程：对不同架构（GPT、Gemini、Qwen、DeepSeek）的情绪向量进行横向比较，会不会发现系统性的情绪偏差——比如某些模型天生更「焦虑」、某些更「冷漠」？这不仅是学术问题，更是产品选型和安全评估的实际需求。
-
- Feb 2021
-
github.com github.com
-
Compared to existing Ruby desktop frameworks, such as Shoes, Bowline's strengths are its adherence to MVC and use of HTML/JavaScript.
-
- Jun 2020
-
arxiv.org arxiv.org
-
Altmann, E. G. (2020). Spatial interactions in urban scaling laws. ArXiv:2006.14140 [Physics]. http://arxiv.org/abs/2006.14140
-
- May 2020
-
psyarxiv.com psyarxiv.com
-
Rotella, A. M., & Mishra, S. (2020, April 24). Personal relative deprivation negatively predicts engagement in group decision-making. https://doi.org/10.31234/osf.io/6d35w
-