HackerNews中文版

Hello HN，我是一名大学生，正在构建一个用于个人使用的金融情报终端。目标是在“内幕消息”和社交媒体上的情绪变化成为主流头条新闻之前捕捉它们。我很乐意听取您对架构和逻辑的反馈。技术栈：后端：Python (PM2 管理) LLM：OpenAI GPT 5.2 用于高层次分析 + GPT-5-mini 用于新闻过滤和市场数据收集 (通过 API) 前端：Next.js + Tailwind + Recharts 架构 (有趣的部分)： 1. 收集器我没有立即调用 LLM，而是每 30 分钟运行一次原始抓取器，目标是： - Nitter 实例 (用于 Twitter/X 数据，没有 API 限制)。 - GNews RSS (用于官方头条新闻)。 - DuckDuckGo (用于一般论坛讨论)。 - 1 分钟 OHLC 数据 (通过 yfinance) 以监控价格微观结构。 2. Agentic 系统我将分析分为两个角色： - 市场 Agent：分析 30 分钟窗口的 1 分钟 K 线数据。它寻找“V 型反弹”、“闪崩”或“量能耗尽”等模式 (这些是简单的百分比变化指标所遗漏的)。 - 新闻 Agent：分析来自抓取器的消息和事件，并可以确定是否在市场开盘期间唤醒待命的高级 Agent 以应对“紧急情况”。 - 高级 Agent：接收清理后的新闻流 + 市场 Agent 的技术总结。它生成一个情绪得分 (-10 到 +10) 和一个理由。如果价格在未来几个小时内可能会发生很大变化，它会创建一个“红色警报”。 - 待命 Agent：分析新闻并在互联网上搜索证据，以确定是否向用户发送警报。 3. 前端为了更好地显示信息，我使用 Next.js + Tailwindcss 进行了前端代码编写。即将发布带有 i18n 的更新版本。我对 HN 的问题：延迟与深度：目前，AI 分析周期需要大约 3 分钟。对于“波段交易”来说，这很好，但如果有一种更好的模式可以流式传输部分更新到前端，而无需等待完整的分析完成，这会有帮助吗？幻觉风险：我强制 LLM 验证日期，但有时它仍然将“重新发布的旧闻”视为新事件。你们如何为新闻 Agent 设计验证层？实用性：我刚刚完成了这个 Agentic 系统，并且根据 Agentic 系统的信息，这是我第一天交易，目前盈利 +0.8%。我很乐意听取有更多交易经验的人的建议。此外，如果您想预览系统的输出，请随时与我联系。一些截图在这里：https://x.com/CLCKKKKK/status/2006085046269337799?s=20 我的电子邮件：yiz29@illinois.edu 谢谢！

查看原文

Hello HN,I’m a college student building a financial intelligence terminal for personal use. The goal is to capture "whisper numbers" and sentiment shifts in social media before they hit mainstream headlines.I would love your feedback on the architecture and logic.The Stack:Backend: Python (PM2 managed)LLM: OpenAI GPT 5.2 for high level analysis + GPT-5-mini for news filter and market data collection (via API)Frontend: Next.js + Tailwind + RechartsThe Architecture (The interesting part):1. The CollectorInstead of hitting the LLM immediately, I run a raw scraper every 30 minutes targeting:- Nitter instances (for Twitter/X data without API limits).- GNews RSS (for official headlines).- DuckDuckGo (for general forum chatter).- 1-min OHLC Data (via yfinance) to monitor price micro-structure.2. The Agentic SystemI split the analysis into two roles:- Market Agent: Analyzes the 30-minute window of 1-min candle data. It looks for patterns like "V-shape recovery," "Flash crash," or "Volume exhaustion" (things a simple % change metric misses).- News Agent: Analyzes the messages and events from the scrapper, and it can determine whether to wake up on-call senior agent for "emergency" during market open time.- Senior Agent: Receives the cleaned news stream + the Market Agent's technical summary. It produces a Sentiment Score (-10 to +10) and a rationale. It creates a "red alert" if the price will probably be changing a lot in the next several hours.- On-call Agent: Analyzes the news and search the internet for proofs and determine whether to send alert to users or not.3. The FrontendTo better display information, I vibe coded a Next.js + Tailwindcss frontend. An updated version with i18n will soon be published.My Questions for HN:Latency vs. Depth: Currently, the AI analysis cycle takes ~3 minutes. For "swing trading" this is fine, but will it help if there's a better pattern to stream partial updates to the frontend without waiting for the full analysis to complete?Hallucination Risks: I force the LLM to verify dates, but sometimes it still treats a "re-posted old news" as a new event. How do you guys architect verification layers for news agents?Practicability: I just finished this agentic system, and it's my first day trading according to the info from the agentic system and it's currently +0.8% profit. I'd love advice from someone with more trading experience. Also, feel free to reach out to me if you want a preview of the system's output.Some screenshots here: https://x.com/CLCKKKKK/status/2006085046269337799?s=20My email: yiz29@illinois.eduThanks!

Ask HN: 我的多智能体金融情绪分析架构