Joined May 2024
Photos and videos
coding python retweeted
如果我要在90天内找到一份20万美元的AI工程师工作,我不会去读学位。 我会精通这10个GitHub仓库。 1. awesome-llm-apps 生产级AI指南。RAG、智能体、多模态应用,附完整代码。10.6万 stars。 仓库 → github.com/Shubhamsaboo/awes… 2. LangChain 基础框架。被Klarna、Replit、Elastic及2026年大多数AI创业公司用于生产环境。 仓库 → github.com/langchain-ai/lang… 3. LangGraph 驱动生产智能体的编排层。资深AI工程师岗位描述中的必备技能。 仓库 → github.com/langchain-ai/lang… 4. CrewAI 多智能体协调。财富500强团队首选框架。 仓库 → github.com/crewAIInc/crewAI 5. Ollama 在自己机器上运行任何开源LLM。学习模型工作原理的最快方式。 仓库 → github.com/ollama/ollama 6. awesome-mcp-servers MCP是2026年所有主流AI实验室采用的标准。掌握它让你领先99%的工程师。 仓库 → github.com/punkpeye/awesome-… 7. Qdrant 大规模生产RAG使用的向量数据库。嵌入和语义搜索是AI岗位的必需技能。 仓库 → github.com/qdrant/qdrant 8. AI-Agents-for-Beginners 微软免费12课程,教建立智能体。真实代码、真实练习、真实面试准备。 仓库 → github.com/microsoft/ai-agen… 9. system-design-primer 生产级AI就是系统设计。FAANG工程师用来面试准备的仓库。 仓库 → github.com/donnemartin/syste… 10. awesome-claude-code 这个工具的使用指南,现被FAANG、OpenAI、Anthropic及大多数YC创业公司内部使用。 仓库 → github.com/hesreallyhim/awes…
31
173
714
37,369
coding python retweeted
> be 19 yo student from Japan > built a Claude Code trading bot in 2 days > uses iPad as second monitor > scans 50 Polymarket markets > syncs BTC data from Binance > finds pricing errors before humans do > one night: $6,732 > started with $68 > total profit $1.7M why are people still trading manually?
A 19-year-old student from Japan demonstrated his automated trading robot, which he built using Claude Code. Claude handled most of the tedious work. This robot tracks price discrepancies across more than 50 markets on Polymarket, while simultaneously synchronizing data from Binance via OpenClaw to analyze ultra-short-term BTC trends. This is where the excess profit comes from. He created the script in just 2 days, using only an iPad as a secondary monitor during the process. System architecture: Claude Code is responsible for strategy generation and closely monitoring pricing errors on Polymarket. OpenClaw handles trade execution and synchronization with Binance for BTC analysis. 0 manual intervention, fully automated execution. Performance snapshot: In one night: 3 trades opened, 2 trades automatically closed. Example trade: BTC short on the 15-minute level, entry 0.31, exit 0.79. Net profit for the evening: $6,732 Strategy logic: Specializes in capturing profits from pricing errors between markets. High-frequency execution, each trade uses minimal edge in risk/reward ratio. Net trading volume compounds profit. Comparative reference: k9Q2m profile: polymarket.com/@k9q2mx4l8a7z… Copytrading in one click:t.me/AresProTradingBot?start… Annual trading volume: about 54,356 trades Profit: about $1,720,270 Strategy: arbitrage Evolution process: Started with a few hundred dollars Initially only simple blind trade copying Then independently built a customized monitoring and execution system Risk management: Automatic shutdown for protection during liquidity anomalies Emergency position closing requires manual confirmation Example loss: about 3% drawdown during a panic wave Current operating state: Fully autonomous self-hosted system Monitoring exclusively via notifications Almost no need for human intervention Starting capital: about $68
67
412
3,945
677,921
coding python retweeted
Apr 28
GitHub 上有一份被无数自学者当作“计算机本科替代方案”的课程清单:open-source-cs,已拿下 2 万 Stars。 它把 MIT、斯坦福、普林斯顿等顶尖高校的免费公开课,按传统 CS 本科培养路线重新编排:从入门到进阶、从理论到工程,一条清晰的学习路径直接铺好。 编程、数学、系统、算法到应用全覆盖;每门课还贴心标注学时、难度与前置要求,让你少踩坑、不迷路。 GitHub:github.com/ForrestKnight/ope… 你将学到: - 计算机科学基础:从 Harvard CS50 打牢地基 - 编程能力:Duke、华盛顿大学的 Java 与编程语言体系训练 - 数学底座:MIT 微积分 UT Austin 线性代数,补齐硬核必修 - 系统原理:从零构建现代计算机,理解“它为什么这样跑” - 算法与理论:普林斯顿算法与 CS 理论,练出解题与证明能力 - 方向应用:软件工程、机器学习、数据库、密码学等实战领域 所有课程来自知名大学公开课平台,完全免费。适合想按本科体系系统自学计算机科学的人:按这张地图走,就不再靠运气学习。
Community note
Los enlaces apuntan a Coursera que dejó de ser gratuito en mayo de 2025, ahora es obligado pagar la tasa. Además, son enlaces de afiliado prácticamente el 90% coursera.org/about/affiliat… coursera.support/s/article/lear…
39
842
5,865
323,728
coding python retweeted
Sci-Hub is an evil website that pirated 85M research papers and made them freely available And now they've added AI to their database to make Sci-Bot. It answers your questions using latest, full-text articles. But DO NOT use it. We should all try to make billion-dollar academic publishers richer. I'm putting the link below so you know how to avoid it.
836
8,903
46,837
4,947,234
coding python retweeted
🚨 Anthropic's own team just showed how to actually use Claude Code properly. 30 minutes. free. the person who created Claude Code. watch the workshop. bookmark it. worth more than every $500 course you almost bought. you've been using Claude without knowing 40 of its commands. Then read the guide below.
262
4,962
29,910
7,308,645
coding python retweeted
A SINGLE CLAUDE.md FILE JUST HIT #1 ON GITHUB TRENDING. 82,100 stars. 7.8k forks. zero dependencies. Bookmark this before you forget. And your Claude will start working differently. 4 principles. one file. Karpathy's LLM coding habits. distilled. > think before coding. > simplicity first. > surgical edits only. > goal-driven targets before starting. swap it into your CLAUDE.md today. your Claude Code becomes a different tool. Read it today. Link below. Claude → Skills → CLAUDE.md → Better Code → Better Systems → Money
🚨do you understand what the Head of Anthropic Coding Agents just dropped. 30 minutes. more value than 100 paid courses. not a course. not a tutorial. how top AI researchers actually build. here's the part nobody is talking about: > real workflows. not theory. > vibe coding from the source. > how they think, build, and ship with agents. watch this before you write another prompt. before you build another agent. before you touch another tool. 30 minutes. bookmark it. watch it today. this one changes how you use AI for good.
68
490
8,403
4,604,734
coding python retweeted
HELP
8
283
2,817
36,385
coding python retweeted
promoting my saas on X feels like
77
11
210
6,823
coding python retweeted
pondering
10
396
3,189
58,176
coding python retweeted
Mar 27
Claude watching me write code manually after I hit the daily limit

399
5,863
80,291
3,671,461
coding python retweeted
lawyer up buddy
16
520
4,896
56,326