2026年的年初，这几天所有的新闻都是关于委内瑞拉总统马杜罗被美国抓捕的信息。我所了解的相关时政 YouTuber 几乎都做了这个主题的节目。 在高强度观看了大量内容之后，我也来说说我的想法。 不同观点的博主在看到这个事情之后，每个人的想法差别还是比较大的。 但是，他们的想法并没有因为这件事而发生很大的改变。基本上，每个人还是保持着他们此前的想法。 或消极，或乐观。 所以我认为这件事情对...

AI Slide Generation Workflow Practice I followed baoyu.io’s workflow for generating editable AI slides and created a story slide myself. The result turned out good. References Most Valuable P...

New Year, More Posts I’m going to write more posts in 2026. More posts means lower quality for each one, but I think the overall value will increase. Writing is hard, and the only way to really pr...

TL;DR: I use Claude Code’s skill system to replace Playwright MCP for browser automation, based on Armin Ronacher’s implementation. Same functionality, but without MCP eating up your context (Playw...

Content Plan Updated This weekly digest has now reached its 17th edition, which means 4 months of reading. I think it is really a lot, and a lot about AI. I have learned tons of ideas from various ...

AI Nondeterminism in LLM Inference Through the article “Defeating Nondeterminism in LLM Inference”, I learned about an underlying factor in model output instability: non-batch-invariance. This non...

AI Development Speed Is Not a Bottleneck Product development, in essence, is continuous discovery. First, we aim to validate the idea, then we switch to validating whether any given change bring...

AI News DeepSeek-V3.1: I have tried this model several times, the results are not good at all. Gemini 2.5 Flash Image: Maintain character consistency Prompt based image editing Multi-image ...

AI Evaluation Asymmetry of verification and verifier’s law How to do things becomes less relevant if we can set a good verification/evaluation against the output of LLM, then let LLMs figure out h...

AI AI and Humanity 1910: The Year the Modern World Lost Its Mind Fast pacing of technology developments gave people anxiety and new perspective about society in 1910. I want to make two predictio...