GWGaoying Wang Let’s talk

THE BLOG / RESEARCH & PRACTICE

Notes from
the work.

Research, experiments and lessons from building AI systems. How models meet people, products and the real world.

AI SYSTEMS · HUMAN JUDGMENT · ENGINEERING
LATEST NOTE

When RPA Meets CAPTCHA: From an AI Vision Idea to an Auditable Human-in-the-Loop Workflow

This design note examines an unimplemented RPA idea: using AI to interpret text and a checkerboard aligned with pointer-motion units to express click or drag coordinates. It then explains why third-party production CAPTCHAs should not be treated as ordinary UI automation, and reframes the idea as a safe workflow built around official APIs, test credentials, human review, coordinate calibration, confidence gates, and audit logs.

Read the note

More notes

03 NOTES
02
Field note

Will World Models Arrive Before AGI?

This essay argues that domain-specific world models will probably mature before AGI that can act safely in open physical environments, while a complete universal world model may not arrive as a separate system before AGI. The practical safety unit is an assurance stack combining prediction, scenario generation, constraints, monitoring, and staged deployment.

↗

THE BLOG / RESEARCH & PRACTICE

从实践出发，
记录思考。

记录构建 AI 系统过程中的研究、实验与经验，以及模型与人、产品和现实世界相遇时的问题。

AI SYSTEMS · HUMAN JUDGMENT · ENGINEERING
最新文章

RPA 遇到验证码：从 AI 视觉设想到可审计的人机协作流程

本文记录一个尚未实施的 RPA 设计设想：文字界面可由 AI 辅助理解，点击或拖动界面可用与鼠标步长对齐的棋盘网格表达坐标。文章进一步解释为什么生产环境中的第三方 CAPTCHA 不应被当作普通 UI 自动化，并将该设想收敛为官方 API、测试密钥、人工介入、坐标校准、置信度门控和审计日志组成的安全工作流。

阅读全文

更多文章

03 NOTES
02
Field note

世界模型会先于 AGI 诞生吗？

本文提出一个经过收敛的判断：领域级 world model 大概率会先于面向开放现实世界的 AGI 成熟，但完整通用 world model 不一定独立早于 AGI。真正的安全关键不是单个模型，而是 world model、场景生成、约束验证和分阶段部署组成的 assurance stack。

↗