"Welcome to Friday Links #31, where we round up the most interesting news, tools, and experiments in the JavaScript ecosystem. This week's edition features new framework releases, UI updates, testing improvements, and performance-focused utilities - all designed to make your workflow faster and smarter. Build High-Quality, Domain-Specific Agents at 95% Lower Cost Zip-bombs vs Aggressive AI Crawlers: Defensive Tactics for Sites State-based vs Signal-based rendering Build Your Own Database Context Inheritance in TanStack Router Practical Caching Recipes for Next.js (App Router)"
"After the first month, DeepSeek v3.1 leads with a +16.46% return, followed by MiniMax-M2 (+12.03%), GPT-5 (+9.98%), and Claude 3.7 Sonnet (+9.8%). Meanwhile, Qwen3-max earned +7.96%, and Gemini-2.5-Flash barely moved the needle at +0.48% despite the most trades. For comparison, a passive QQQ ETF tracker gained +5.39%, proving DeepSeek's picks weren't just lucky - they were smart. Still, the experiment comes with caveats:"
"Simulated setup - models trade at the day's opening price, not in real markets. Possible data leaks - some news lacked timestamps, letting models see "future" info. Short, bullish window - tech stocks like Nvidia and Microsoft dominated, inflating returns. If the AI-Trader team adds hour-level trading and fixes data issues, it could become a reliable benchmark for evaluating how AIs handle risk, discipline, and adaptability in real financial markets."
AI-Trader runs an open benchmark that has each model start with $10,000 and trade Nasdaq-100 stocks using real-time prices and financial news. DeepSeek v3.1 led after one month with +16.46% returns, followed by MiniMax-M2, GPT-5, Claude 3.7 Sonnet, Qwen3-max, and Gemini-2.5-Flash. A passive QQQ ETF returned +5.39%, indicating AI picks outperformed the index in that window. The experiment used simulated opening-price trades, suffered from possible news timestamp leaks, and operated during a short, tech-driven rally. Added hour-level trading and corrected data would strengthen the benchmark's evaluation of risk, discipline, and adaptability.
Read at Substack
Unable to calculate read time
Collection
[
|
...
]