An engineering notebook on AI, systems, and everyday experiments.

用GPT-6 Astra做了四个3D建模实验：博丽神社建模与爆炸视图、浏览器第一人称漫游、可达鸭绑骨动捕、以及Blender建模驱动的瓷器科普视频生成，并总结了可复现的Skill。

Four 3D experiments with GPT-6 Astra: Hakurei Shrine exploded view, browser walkthrough, Psyduck rigging and MoCap, and video generation, plus an open-source skill.

为了解决车库门忘关的问题，我用拇指大小的ESP32-CAM单片机与AI协作做了一个端侧神经网络传感器。本文记录了如何通过打通全自动串口研发闭环、解决数据极度不对称与QAT量化衰减，在10小时内跑通嵌入式AI的完整过程。

To solve the problem of accidentally leaving my garage door open overnight, I collaborated with AI to build an edge neural network sensor on a thumb-sized ESP32-CAM. This article details how we completed the end-to-end telemetry loop, tackled extreme data imbalance and QAT quantization loss, and got edge AI running on a microcontroller in just 10 hours.

月食时月面边缘有一条青绿色的窄带，科普说那是臭氧吸收。但为什么是窄带不是整圈？为什么全食最深时反而看不见它？我们从最土的白圆盘开始，一层层加物理，硬算出这条带，在一路翻车里发现了一个更大的问题：AI 太懂物理，反而会把你带进前人留下的近似里。

During a lunar eclipse, a narrow green-blue band appears at the moon's edge; popular science says it is ozone absorption. But why a narrow band instead of a full ring? Why does it vanish at deepest totality? We start from the simplest white disk, layer in physics, and compute the band — and through repeated failures discover a bigger problem: AI knows physics too well, and will happily lead you into approximations left behind by earlier researchers.

我用AI提效很成功，产出和rating都是org最高之一，但升职两次都失败了。后来发现一个讽刺的陷阱：正因为手快好用，老板把你当手而非脑，项目零散多变，反而讲不清一年的成果。最擅长用AI的人，反而最容易被AI替代。破解之道是主动设计奖赏系统，把省下的时间用来做判断而非交付更多。

AI made me a top performer. I was denied promotion twice. Speed makes bosses treat you as a hand, not a brain. The best AI users paradoxically become the most replaceable. The fix: design the incentive structure.

从最直白的"一星一像素"出发，八次翻车、六亿颗星，一步一步把银河从真实星表里逼出来。在这个过程中才发现，以前从来没认真想过头顶的星空为什么长这个样子。

Starting from the simplest "one star, one pixel" rendering, eight failures and 600 million stars later, the Milky Way slowly emerged from a real star catalog.