1
A New Trick Reveals AI Models’ Inner Thoughts
新技巧让AI的“内心独白”无所遁形，还疑似抓到模型间蒸馏痕迹
Researchers devised a way to extract “reasoning traces” from Claude, GPT, and Gemini. What they found, they say, indicates that some Chinese AI may be…
2
Show HN: LLM Thought Visualization
围观大模型「脑内小剧场」，实时透视每一步推理思维，神器级可视化工具
Article URL: https://github.com/ninjahawk/Subtext Comments URL: https://news.ycombinator.com/item?id=48811892 Points: 7 # Comments: 0
3
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
利用思维链过程嵌入隐秘水印，为AI模型提供高效且不易察觉的版权保护新方法，已被ICML 2026接收。
arXiv:2605.28890v1 Announce Type: cross Abstract: Large Language Models with Chain-of-Thought reasoning capabilities represent valuable intellectual p…
4
Does AI Know How Many Tokens It Is Burning
AI按token计费看似精确，但背后推理过程复杂且隐藏，揭露了费用计算的模糊性。
The strange thing about the modern AI bill is that it looks precise while the work behind it feels mysterious. A user types a short request, a model t…