Fed 3 years of messy WeChat history into GPT-4.1's 1M token window—it synthesized themes, generated insights, and wrote a cohesive book about AI collaboration.
从数据挖掘到认知炼金：用OpenAI Deep Research（模拟）购车决策全流程
通过模拟购车场景实测OpenAI Deep Research，展示其如何大幅提升调研效率、解放脑力进行更深层思考，以及重新定义问题边界的认知炼金能力。
From Data Mining to Cognitive Alchemy: A Full Simulated Car-Buying Workflow Using OpenAI Deep Research
A hands-on exploration of OpenAI Deep Research through a simulated car-buying scenario, demonstrating how AI elevates research efficiency and enables deeper strategic thinking about negotiation and decision-making.
DeepSeek r1使用随感
对比GPT-4o和o1评测DeepSeek r1，发现其在指令遵循和思维深度上不及第一梯队，但在中文表达和创意写作方面展现出独特优势。
Reflections on Using DeepSeek r1
A critical review of DeepSeek r1 comparing it to GPT-4o and o1, finding it lacking in instruction following and reasoning depth, but exceptional in Chinese language mastery and creative writing.