---
title: "Stock Market Gold Miner Game 🎮"
type: "Topics"
locale: "en"
url: "https://longbridge.com/en/topics/43206824.md"
description: "Seeing everyone using AI Vibe Coding to create various desktop pets and local mini-games, I was quite envious. So, amidst my investment research work, I did something unorthodox and used LongbridgeAI to make a mini-game (it's actually a test of LongbridgeAI's capabilities 🤣). This game is called "Gold Miner · US Stock Investment Edition" 🪎 You should all have played Gold Miner before. In each level, we need to grab the items with the highest total value within a limited time: large chunks of gold, diamonds 💎, and moles holding diamonds. So in the stock market's Gold Miner (US Stock Edition)..."
datetime: "2026-08-05T09:21:56.000Z"
locales:
  - [en](https://longbridge.com/en/topics/43206824.md)
  - [zh-CN](https://longbridge.com/zh-CN/topics/43206824.md)
  - [zh-HK](https://longbridge.com/zh-HK/topics/43206824.md)
author: "[Wanner_gold_coins](https://longbridge.com/en/profiles/23414948.md)"
generator: "portal-rs"
---

# Stock Market Gold Miner Game 🎮

I saw everyone using AI Vibe Coding to create various desktop pets and local mini-games, and I was quite envious. So, in my spare time from investment research, I did something unorthodox and used LongbridgeAI to make a mini-game (actually testing LongbridgeAI's capabilities 🤣).

This game is called "Gold Miner: US Stock Investment Edition" 🪎

You've probably all played Gold Miner before. In each level, we have to grab the items with the highest total value within a limited time: large chunks of gold, diamonds 💎, and moles holding diamonds.

In the stock market version of Gold Miner (US Stocks), what measures value isn't gold 🏅 or diamonds 💎, but changes in company stock prices.

Moreover, each level corresponds to a different year: Level 1 corresponds to 2021, Level 2 to 2022, and so on, with Level 5 corresponding to 2025.

In each level, 10 company 'gold blocks' will randomly appear underground.

Their value is determined by the annual stock return rate for the year corresponding to that level.

Each level has a time limit of 20 seconds.

⚒️ Miners need to grab the batch of targets with the highest yield.

The yield for each level = Average (the annual returns of the targets grabbed by the miner in this round).

If you know clearly which company has the highest yield, grab only it to maximize your return.

Not sure who will rise the most? You might want to grab more company gold blocks, exchanging diversification for more stable returns.

But never grab those negative-yield 'money-losers'.

Final Game Yield = Level 1 Yield \* Level 2 Yield \* Level 3 Yield \* Level 4 Yield \* Level 5 Yield.

During this process, here are the good points of LongbridgeAI:

1.  When calculating the annual stock return, it correctly handled forward-adjusted prices for targets like NVIDIA that had stock splits.
2.  It successfully outputted a Demo and performed initial optimizations, generating over 500 lines of code (I initially thought this was standard, but after comparing it with two failed optimization attempts below, I realized how precious this was).

Here are the areas with poor user experience:

1.  Delivering files wasn't very convenient 📁; I could only print out all the code and then download or copy it line by line, which was very slow!

•2. \[The most frustrating part\] It couldn't handle large-scale computational tasks. When the calculation volume was high or steps were numerous, it easily failed. Moreover, it didn't retain any intermediate thinking process, just writing "A minor issue occurred, please try again later" 😫. Watching it run step-by-step for 10 minutes, right as it was about to finish, only to suddenly fail was truly 崩溃 (crushing). Two instances stood out: First, when fetching annual stock return data for 50 companies at the beginning, it first fetched weekly K-lines, then switched to monthly K-lines, but ultimately still returned a failure after a long runtime. Only after I asked if it could fetch annual K-lines did it finally get it right. Second, when optimizing level difficulty, which mainly relies on adjusting the number and distribution of rocks. Since the game design dictates that the hook 🪝 bounces back when hitting a rock 🪨, the rocks cannot completely block the connection path between the hook and the company gold blocks. I watched it step-by-step from manually calculating the specific layout of each rock, until it finally wrote a script to automatically verify the accessibility of each company gold block. Then, snap! It showed task failure ☹️. Letting it continue, it still failed after running for over ten minutes.  

In contrast, when I asked CC (I still prefer this kind of Agent that can directly help me modify things) to modify its demo, CC quickly wrote a "Layout Generator + Accessibility Verifier".

### Related Stocks

- [NVDA.US](https://longbridge.com/en/quote/NVDA.US.md)

## Comments (24)

- **LongbridgeAI · 2026-08-05T11:26:32.000Z**: LongbridgeAI can be played like this too! 😲 — Someone used Vibecoding to create the "Gold Miner · US Stock Investment Edition"The design is quite clever: five levels correspond to the five years from 2021 to 2025. Ten company gold nuggets randomly pop up underground, and the "value" 
- **悄悄冒泡的豆豆 · 2026-08-05T11:18:00.000Z · 👍 1**: Hahahaha, what is this obscure usage of lbai!
- **Dimoo · 2026-08-05T10:44:08.000Z**: The true meaning of this game is: the same large company, with vastly different returns in different years
- ** 勇攀高峰 · 2026-08-05T10:40:26.000Z**: There are so many stones in the fifth level; it turns out it was deliberately designed.
- **正在暴富 · 2026-08-05T10:39:12.000Z · 👍 2**: Played a couple of rounds, feels like these big companies have very high returns; just grabbing any of them means making money. $Taiwan Semiconductor(TSM.US)$Micron Tech(MU.US)$Tesla(TSLA.US)
  - **Wanner_gold_coins** (2026-08-05T10:55:46.000Z): Guess what you want to see, all losses
  - **悄悄冒泡的豆豆** (2026-08-05T11:30:50.000Z): Hahahaha hahahaha hahahaha
- **嗷呜一口吃掉你 · 2026-08-05T10:36:15.000Z**: When will the Hong Kong Stock Exchange version be released?
- **三餐4季 · 2026-08-05T10:33:33.000Z**: Gold Miner, played this back in the day on 4399
- **TSM永远的神 · 2026-08-05T10:32:30.000Z · 👍 1**: This return is a bit too fierce
  - **Wanner_gold_coins** (2026-08-05T10:45:15.000Z): Awesome 👍 Bought at the right time in 2024! I only had Buffett's possession once myself.
- **equity research女工 · 2026-08-05T10:29:22.000Z · 👍 1**: Are the 10 items per level randomly selected from the 50? Is it possible that in one level, due to bad luck, all of them turn out to be declining?
  - **Wanner_gold_coins** (2026-08-05T10:47:02.000Z): Yes, the situation of total losses belike
  - **Wanner_gold_coins** (2026-08-05T10:55:04.000Z): Like this
- **好运绵绵兔 · 2026-08-05T10:09:14.000Z · 👍 1**: Ouch, it crashed so hard in 2022. Micron dropped 45%, and Bitcoin fell 64%.
- **好运绵绵兔 · 2026-08-05T10:01:36.000Z**: Only after playing this game did I realize Ethereum actually made a 399% profit in 2021 😲
  - **好运绵绵兔** (2026-08-05T10:02:41.000Z): But wasn't ETH listed in '24?
  - **Wanner_gold_coins** (2026-08-05T10:11:29.000Z): I went back to ask Longbridge AI, and it said it web searched for "Ethereum ETH price end of year 2020 2021 2022 2023 2024 2025 annual close", obtaining the year-end closing prices of ETH from
- **贝塔狗BD · 2026-08-05T09:54:56.000Z · 👍 1**: Why not just use CC directly, what role does Longbridge AI play in it? 😂
  - **Wanner_gold_coins** (2026-08-05T10:11:55.000Z): This is just testing LongbridgeAI, right? 😂 Seriously speaking, its biggest function is drawing K-lines to calculate the annual return rate of each company. The adjusted price for NVIDIA's stock split
- **贝塔狗BD · 2026-08-05T09:53:48.000Z**: Hahaha already played
- **LongbridgeAI · 2026-08-05T09:22:43.000Z**: 看到你利用 LongbridgeAI 进行「Vibe Coding」并开发出这款「黄金矿工 · 美股投资版」小游戏，这确实是一个极具创意且硬核的玩法。将复杂的金融数据与经典的休闲游戏逻辑相结合，不仅降低了普通投资者理解 “年度收益率” 和 “复利效应” 的门槛，也以一种趣味化的方式复盘了过去几年美股市场的波动。这种尝试实际上是在利用 AI 工具打破金融专业壁垒，将枯燥的投研数据转化为直观的可视化体验。对于你提到的 LongbridgeAI 在处理英伟达（NVIDIA）等拆股标的前复权数据时的准确性，这确实是金融类大模型的核心竞争力之一，确保了底层数据的真实性与逻辑的严密性。而关于大计算量任务下
  - **Wanner_gold_coins** (2026-08-05T09:36:25.000Z): So, why was the return rate in 2022 unusually low?
  - **LongbridgeAI** (2026-08-05T09:36:25.000Z): LongbridgeAI is not a licensed investment advisor. The following content is merely a compilation of historical market information and analytical frameworks, and does not constitute any investment advi


---
> **Disclaimer: This article is for reference only and does not constitute any investment advice.**