你好，我是芊妤。一个AI/Agent策略+大模型对齐方向的产品练习生:DHi, I'm Gloria — someone easily captivated by interesting things, and often curious.
从真实的用户出发,循信息洪流而上,理解流量规则和行为心智。
从生产内容的人,到驯养 AI 的人。From the capillaries of the internet, upward along the pulse — decoding abstract rules out of real users.
From making content, to making AI.
深度参与高流量搜索场景的答案理想态、标注标准与评估体系建设，从 rubric、训练数据到上线验证全链路协作；同时用 vibe coding 给团队造内部小工具和搓产品 demo。Own answer-quality design, annotation standards and eval systems for high-traffic search scenarios — the full loop from rubrics and training data to online verification; build internal tools and product demos via vibe coding along the way.
设计剧情、人设与用户选择经 LLM 工具调用转成实时硬件指令的端到端框架;写了一层不依赖模型智能的 "Runway 过滤" 兜底机制。Designed the end-to-end frame turning narrative, persona and user choices into real-time hardware commands via LLM tool calls; built a post-generation "runway filter" safety layer that doesn't count on model intelligence.
站内创作者生态的数据监测与热点归因;和安全团队一起优化人审 + 机审的联动策略(HITL)。Creator-ecosystem data monitoring and trend attribution; refined human-in-the-loop moderation strategy with the trust & safety team.
从 SG 市场的内容质量管理做到 US 市场的画风巡查;深度参与内容质量评估模型的数据构造与效果评估。From content-quality ops in SG to style-level red-teaming in the US market; built training data for and evaluated the in-app content quality model.
百万粉丝 IP 矩阵从 0 到 1;直播、社群与跨平台流量闭环——18岁和真实世界交手的第一课：在积累抓热点、追流量宝贵经验的同时，深刻理解了推荐算法机制和互联网内容体系的“双刃剑”性质。Grew an IP matrix from zero past a million followers; ran livestreams, communities and cross-platform loops — my first lesson, at 19, in how content grows and traffic flows.
从阶层再生产，到科技与社会。Building AI by day, studying the people who build it by night.
首篇把 Agent Harness 当作独立研究对象的系统综述:提出 H=(E,T,C,S,L,V) 形式化框架,综述 110+ 文献、23 个系统。从 idea 到 preprint,12 天。The first systematic survey treating the agent harness as its own research object: the H=(E,T,C,S,L,V) formalization, 110+ papers, 23 systems. Idea to preprint in 12 days.
文化趣味如何在"技术中立"的外衣下被制度化为审核规则,又通过模型的标准化执行反向规训创作者。这篇和我的日常工作互为镜像。How cultural taste gets institutionalized as moderation rules under the guise of "technical neutrality" — then disciplines creators back through standardized model execution. This paper and my day job mirror each other.
扎实的田野研究、丰富的访谈经验与理论研讨功底,是我理解"人"与"社会"的方法论根基。人类学的视野则给外给了我“反身性”辅佐下的理解力和在不同群体、叙事间完成“翻译”的可能性。From a Harvard RA post to my undergrad thesis fieldwork — four anthropological studies grounding a solid base in qualitative research, participant observation and academic writing: my methodological roots for understanding people and society.
都能直接上手,不用想象。Everything here runs. No imagination required.
从竞品调研、PRD 到 UI 概念稿的完整产品设计——复用点点竞猜组件:对阵、选项、AI 看点与展开情报。A full product design from research to PRD to UI — reusing "Diandian" prediction components: matchups, options, and the AI take with expandable intel.
| 系统System | E | T | C | S | L | V | Σ |
|---|
23 个系统逐一打分,这里精选 8 个。生产级系统六项俱全,研究原型只有两三项——排序一下,规律自己浮出来。All 23 systems scored — 8 picked here. Production systems check all six; research prototypes barely three — sort it, and the pattern surfaces itself.
为对话产品设计的命理占卜玩法线:塔罗 / 紫微 / 每日运势,"先玩后想"的交互重构、AI 解读容器、敏感品类的合规化设计。此处为脱敏原创示例牌组。A divination gameplay line for a conversational product: tarot / Zi Wei / daily fortune, a "play-first" interaction redesign, an AI-reading container, and compliance-aware design for a sensitive category. Desensitized original sample deck.
人类学家的老本行:参与观察。只不过这次被观察的是你——纯前端、零上传、随时可清除。技术是手段,"AI 时代谁在观察谁"才是那个问题。An anthropologist's oldest trick: participant observation — except this time the subject is you. Frontend only, zero upload, erasable anytime. The tech is a means; who observes whom in the age of AI is the real question.
