sunlc.ai

HODLer/Defi Farmer❌/Quant❌/Arbitrager❌ Founder Of Bewin Quant (An AI-Driven Quantitative Hedge Fund)

1Following

153followers

Feed

"Old Sun Takes You to Build a Financial Terminal System Worth Millions 1: Overall Concept and Architecture" I originally promised to start updating yesterday, but got delayed due to some matters. Today, I officially start updating the first article. Although all my code is written by AI, I have always insisted on typing every word of all tweets by hand, not even using typeless, because AI-written articles lack a human touch. The update speed may not be very fast, but I will definitely keep updating. The first article will explain why I want to build this system, the overall concept, the building cost, and the system's overall architecture. 1. Why build this system I not only do various quantitative and arbitrage trading in the crypto space but also invest in US stocks. I have always attached great importance to macro research and need a terminal that can integrate so much information daily for quick browsing and decision-making. When I worked in professional institutions before, the company would provide Bloomberg and Reuters terminals costing over a hundred thousand per year, which obviously individual users wouldn't afford. Now with AI, I want to build one myself. At the beginning of the year, when openclaw was popular, I tried to build a set but eventually chose to abandon Lobster and upgrade to the current terminal. The main reason is that openclaw, as an AI agent, is convenient for handling some daily small tasks, but since most tasks are script-based, it still has randomness and instability issues when processing financial data, which is fatal for financial data that requires extremely high quality. So from March, I started rebuilding this system using codex+claude. This system is tailor-made for me, completely based on my trading strategies, trading varieties, and even my daily routine. The display resolution is customized for my 48-inch 4K screen to ensure that the key information I care about can be displayed on one screen as much as possible. So what you can learn from my entire sharing process is not only the system building process but also my entire investment philosophy, which is far more valuable than just open-sourcing the code. 2. Building cost AI models: claude 200U subscription + gpt 200U subscription + grok 30U subscription (from Twitter membership). Mainly use claude's opus 5 max for overall system architecture design and functional module design, then hand over to codex's gpt 5.6 sol max for development and self-testing, and finally to claude for final review and acceptance testing. Server: A MAC MINI M4 16G is sufficient, built at home, then accessed externally via Cloudflare. Specific details will be explained later. Data sources: The system currently has nearly 30 external data sources, most of which are free. The only paid ones are FMP's 20U subscription and IB's 10U data fee, which already meet most needs. 3. System architecture In one sentence: a terminal that integrates crypto + US stocks + macro three main lines. The system adopts a completely decoupled front-end and back-end architecture: Back-end is fully encapsulated in Python as Fast API Front-end uses React + Ant Design framework Database uses ClickHouse Development and deployment are done entirely with Docker. Current system architecture includes: 9 crypto exchanges (unified access via CCXT) 26+ external data sources covering market data, macro data, on-chain data, Twitter news, on-chain anomalies, AI-related news, etc. 40+ work processes running in the background to update various data and indicators regularly 213 US stock AI-related research targets 78 data tables in the backend ClickHouse Over 560 configuration and runtime items It can be said to be very finely split. Current system functional modules mainly include: The overview page can display all the core data I care about on one screen, including macro indicators, crypto indicators, major event news, watchlist market data, arbitrage opportunities, and system status. The arbitrage page shows crypto positive/negative fee rate arbitrage, US stock and RWA target arbitrage, futures-spot premium, OI anomalies, and other important information. The US stock page shows over 200 AI-related targets I follow, with a focus on 30 core targets. This is the core module of my entire system and an important basis for my US stock investment decisions. The IB account and crypto account modules allow easy viewing of all my holdings spread across various exchanges and sub-accounts. The Twitter news module uses grok to collect AI and macro news hotspots I focus on every morning and evening, then uses LLM to summarize and organize them into Twitter morning/evening reports at 7:30 AM and 10 PM respectively. The US stock daily report collects market data and news one hour after US market open (10:30 PM) and at morning close (7:30 AM), organizing them into a daily report based on the data indicators I follow. The above Twitter and US stock daily reports are fully customized according to my daily routine. After waking up at 7:30 AM, I can know the overnight market trends and hot news within 5 minutes. Similarly, one hour after US market open, I can promptly know the day's information and usually make all trading decisions before 11 PM, never staying up late. Additionally, I developed an AI research report library feature. I bought a large number of professional AI industry research reports such as Semi Analysis, FundAI, Damnang, etc. These reports are very large and professional, sometimes hard to fully understand by myself. I put them all into the research report library and use LLM to dissect and analyze them, forming a very powerful research tool. There are also multiple dashboards for options, meme coins, US bonds, USD, inflation, etc., all information I pay attention to daily. Starting tomorrow, I will break down the functions, design ideas, and development methods of each module one by one. Feel free to leave comments for discussion if you have questions. I have a strong dislike for stupidity, so I won't answer overly basic questions or requests for source code directly.

Next, let's talk about my views on the software and application sectors: I believe the software and application sectors are currently severely undervalued and have been completely oversold. After the hardware sector enters a high-level adjustment phase, capital will gradually flow into quality software stocks to restore their valuations. The previously held market logic that large models will kill software companies does not hold, for several reasons: 1. For enterprises, the most important aspects of software are data accuracy and reliable workflows. Products like NOW and CRM have already deeply embedded themselves into many companies' entire workflows. For most enterprises, it is impossible to replace them easily, let alone choose to develop large models in-house. User stickiness is extremely strong. 2. The market worries that the current software seat-selling model will decline due to corporate layoffs. This concern may be valid in the short term, but in the long term, it is actually beneficial. For software companies, transitioning from selling seats to selling usage is not difficult. For enterprise clients, layoffs are due to AI replacement; in the future, software users will gradually be replaced by AI. Originally, one seat worked 5*8 hours per week; after replacement by AI, it will work 7*24 hours, increasing software usage by 4 times. 3. The current AI penetration rate is still very low. The direct users of large models are mainly cutting-edge technical personnel. To enable most people to use AI in the future, the usage form will definitely not be direct use of large models, but rather AI being seamlessly embedded into commonly used software such as chat software, office software, video software, etc. From this perspective, platform companies with massive customers like MSFT and META are currently severely undervalued. 4. The progress of AI large models is a huge negative for programmers but a major positive for software companies. The biggest cost for software companies is labor cost. Within the next 3 years, they can definitely eliminate two-thirds of developers, significantly improving software company profits. 5. Hardware companies sell shovels, software companies dig for gold. Now that all the shovels have been sold, whether gold can be found depends on software companies. I personally am strongly optimistic about MSFT, GOOG, NOW, CRM, and other targets. (META is actually not bad, but I have no confidence in Zuckerberg.) In the future, many innovative application software companies will emerge, and many companies without moats will be eliminated. Therefore, I do not recommend blindly buying IGV, as it contains too many companies.

The storage and chip sectors have sharply corrected these past two days. Those who previously hyped that storage would always be in shortage are now panicking and starting to cut losses. As one of the earliest to call the short-term peak in storage, I now choose to be greedy when others are fearful. I have always been accustomed to left-side trading. My clear trading plan is to start gradually dollar-cost averaging into positions when storage drops 30%, planning to add more between a 30%-50% drop (based on DRAM prices, roughly from 60 to 40). I will pyramid buy more as prices fall, aiming for a final cost closer to 40. Now, let me share my analysis and forecast for the future storage trend (not investment advice): The entire logic is based on the historical development of the U.S., where the big brother eats the meat and the little brothers get the soup, but the little brothers are absolutely not allowed to climb onto the table and eat the meat. Look at Japan and TSMC before. The U.S. will never allow its painstakingly built AI supply chain to be choked by Korean storage. So the core purpose of this round of decline is to seize control of storage. Although the storage manufacturers are in South Korea, the U.S. is a master of financial warfare. Wall Street can effortlessly gain control over SK Hynix and Samsung through financial markets. Starting from Huang Renxun’s VERA RUBIN server, which reportedly requires 1.5T of storage, a group of analysts hyped perpetual storage shortages, igniting the enthusiasm of Korean retail investors to a peak. Then Apple/Microsoft announced price hikes as a signal, followed by SK Hynix’s ADR listing on the U.S. stock market, acting as a hidden executioner striking swiftly—a very smooth harvesting operation. Now, various messages denying storage shortages are being released: sometimes saying VERA RUBIN actually uses only half the memory, 750G; sometimes mentioning various alternatives (see semi analysis articles. I mentioned the concept of “bottleneck” -> “substitute” in previous tweets, which can be referenced). Basically, all the Korean leveraged players with more than 2x leverage are going to be harvested. For the next 10 years, they should just honestly work in factories making storage screws. So, back to the question of whether storage is really in shortage? Here, we need to distinguish between rigid demand and scarcity. For example, food is a rigid demand for everyone, but if you suddenly tell people there will be a 10% global food shortage tomorrow, food prices will immediately surge 100% because those who can’t buy food will starve. Storage follows the same logic. Currently, AI mainly processes text information. In the future, as image, video, and voice functions gradually strengthen, and various physical AI like robots and autonomous driving become widespread, storage will definitely be a rigid demand in the entire industry chain. But if prices skyrocket crazily due to rigid demand and monopoly, it will surely provoke public anger. Do you think TSMC or ASML monopolize? Why don’t they exploit resources so ruthlessly? If you don’t understand, look at TSMC’s statement yesterday, which fully explains the principle of steady and sustainable growth. Why are the Koreans so short-sighted to choose to exploit resources ruthlessly? On one hand, it relates to the national character, historically gambling heavily and lacking long-term vision; on the other hand, they themselves are uncertain whether storage is cyclical, having been hurt too deeply in history, so they can only choose to make a quick profit first. Now, the key points about storage’s future development: 1. The U.S. uses this downturn to pick up Korean bloodied chips. The timeframe is hard to judge, ranging from a few weeks to several months. My strategy is dollar-cost averaging plus adding on big drops. 2. After the U.S. accumulates enough chips, it will push giants like NVDA, AVGO, AMD, and SK Hynix, Samsung to re-sign long-term agreements. Current long-term agreements mainly cover capacity for the next 3 years but do not lock prices, somewhat a tyrannical clause. I think this model is unsustainable and may extend long-term agreements to 5-10 years, but prices can only rise moderately each year to earn reasonable profits (TSMC is a reference example). 3. Koreans will invest money and jointly expand production in the U.S. with major giants, achieving deep interest binding and sharing. Money earned from Americans must stay in the U.S. 4. The consumer electronics side cannot raise prices excessively to cause inflation, nor can it only pursue high HBM profits while not producing DRAM. Controls on ChangXin will gradually relax, and appropriate competitors will be introduced. Once these points are completed, storage will truly come out of the bottom and transform from a cyclical stock to a cash cow. Every word above represents only my personal opinion, all typed by myself without any AI processing, and does not constitute any investment advice. If you disagree, just let the bullets fly for a while and check back in a few months to see if I was right.