1
Show HN: Process your solar eclipse data
用AI辅助编码把448GB日食原始视频变成稳定延时大片，还向全网征集测试数据完善流程。
I've been sitting on some video of the 2024 solar eclipse (448gb specifically). All the interest about the most recent one one in spain inspired me to…
2
You're Probably Overusing "Apply to each" in Power Automate
用XPath代替循环查询，一招让Power Automate流程更高效。
When I started building Power Automate solutions, my answer to almost every array was the same: Use "Apply to each." It worked. My flows ran successfu…
3
LeafData: An Agentic System for Data Migration
LeafData 用智能代理方式简化数据迁移，自动处理复杂映射与转换，让旧系统到新平台的迁移更顺畅。
arXiv:2607.21618v1 Announce Type: new Abstract: Modern data migration relies on JSON configuration to define data connection, pipeline logic, and orch…
4
"The price table most AI cost tools multiply by has one automated test: jq empty
AI成本工具定价表仅依赖一个jq测试，历史价格被覆盖导致费用计算错误，点明数据管理隐患。
Most tools that tell you what your AI usage costs work the same way: count tokens locally, multiply by a shared price table. For most of the ecosystem…
5
一个AI智能体，把我从量化系统的脏活累活里捞了出来
专为量化开发设计，用AI接管数据接入、序列化和内存管理等脏活累活，帮你从“水管工”变回策略研究员，回测与实盘差异也能自动修正。
凌晨两点十七分，策略又一次在实盘里做出了和回测完全相反的操作。我盯着屏幕上的成交记录，脑子里只有一个念头：这破玩意儿到底哪儿出毛病了。 查了四个小时。最后发现，不是模型的问题。是那家数据商推送的行情里，有一笔时间戳错了——把下午三点的成交标成了凌晨三点。于是我的 K 线图上多了一根诡异的下影线，于是…
6
PDFs are one of the biggest bottlenecks in AI workflows
PDF格式正成为AI数据处理的最大阻碍，这款在线工具专为提取结构化知识而生。
Article URL: https://pdf-knowledge-extractor.onrender.com Comments URL: https://news.ycombinator.com/item?id=48546027 Points: 2 # Comments: 0
7
SANA: What Matters for QA Agents over Massive Data Lakes?
对海量数据湖上的问答代理瓶颈进行系统梳理，揭示大规模场景下QA Agent的关键设计要素。
arXiv:2606.13904v1 Announce Type: cross Abstract: Exploratory question answering (EQA) over data lakes requires an LLM agent to discover relevant sour…
8
ETLs in the Era of AI and Sandboxes
探讨AI时代数据ETL与沙盒如何重塑数据处理流程，技术干货值得细读。
Article URL: https://zozo123.github.io/agentic-airbyte/ Comments URL: https://news.ycombinator.com/item?id=48431874 Points: 1 # Comments: 0
9
Page image classification for content-specific data processing
探讨页面图像分类方法，助力特定数据处理的学术研究，适合图像识别与文档分析领域研究者。
arXiv:2507.21114v4 Announce Type: replace-cross Abstract: Digitization projects in humanities often generate vast quantities of page images from histo…
10
How Netflix is Using Multimodal AI to Power Video Search
Netflix用多模态AI将216百万帧原始画面转化为数十亿数据点，颠覆视频搜索体验。
In this article, we will understand how Netflix built this system and the challenges it faced.