When I’m in AI Studio mode (rapid prototyping, lots of experiments), I want to spend my time on prompts, evals and breaking the code — not on re-learning yet another SDK. That’s why I use aisuite for most of my AI projects: One client API across providers Switching models is usually just changing a string like openai:gpt-5-mini → minimax:MiniMax-M2.1-lightning or even local ollama It stays close to the OpenAI-style shape, so it’s easy to adopt Lately I use quite a bit Minimax for coding tasks because it hits a great ratio of price vs quality....
Using Obsidian as a Chess Game Database
The Trading Parallel Chess and trading share a fun truth: you can spend hundreds of hours practicing and still lose. In trading, it’s capital. In chess, it’s ELO. Both require deliberate review of past mistakes to improve. Traders keep journals. Chess players should too. I’ve found that Obsidian—a tool I already use for notes—works perfectly as a chess game database. With the Web Clipper extension and a couple of templates, every game and blunders becomes a searchable, annotated note with an embedded board....
Your .gitignore Won't Protect You From AI Agents
We often assume that adding files to .gitignore or .geminiignore is enough to keep them private. When it comes to local AI agents, that assumption is dangerously wrong. These ignore files are for version control and file search indexing, not a security shield. An AI assistant with access to your local environment can easily read any file, regardless of your ignore settings. A Simple, Scary Test Let’s prove it. Imagine you have a project with a simple ....
Look‑Ahead Traps in Backtesting (Backtrader, MQL, PineScript)
Why This Matters If a backtest seems to “forecast” the future without any explanatory edge, it probably does. The culprit is usually look‑ahead bias: using information you could not have known at the time of the decision. Below are the most common categories, each with a tiny example and a safe fix. These patterns appear in Backtrader, MQL (MetaTrader), PineScript—really in every language and engine. 1) Using Future Bar Values Symptom: The strategy decides using the current bar’s final values (like Close) and assumes an execution that benefits from that same bar’s information....
The Traveling Salesman Problem: From 19th Century Puzzles to Genetic Algorithms
A salesman must visit a set of cities exactly once and return home, minimizing total travel distance. This deceptively simple puzzle—the Traveling Salesman Problem (TSP)—has haunted mathematicians, computer scientists, and logistics planners for nearly two centuries. It remains one of the most studied problems in computational optimization. Historical Origins The TSP’s roots trace to the 1830s, when Irish mathematician William Rowan Hamilton and British mathematician Thomas Kirkman studied related mathematical problems involving traversing graph vertices....
Custom Claude Code Notifications on Linux
If you use Anthropic’s Claude Code CLI, you know the struggle: you run a complex prompt or a long refactoring task, switch to another task, and forget to check back for five minutes. I recently came across Andrea Grandi’s post on how to solve this on macOS using terminal-notifier. Linux has a native equivalent that works perfectly. So… here’s how to set up desktop notifications for Claude Code on Linux....
The Red Queen Effect: Running as Fast as You Can Just to Stay in Place
“Now, here, you see, it takes all the running you can do, to keep in the same place. If you want to get somewhere else, you must run at least twice as fast as that!” This quote, spoken by the Red Queen in Lewis Carroll’s Through the Looking-Glass (1871), became one of the most influential metaphors in evolutionary biology—and increasingly, in technology. Origins: From Victorian Nonsense to Scientific Theory Lewis Carroll (Charles Dodgson) was a mathematics lecturer at Oxford when he wrote Through the Looking-Glass....
My Go-To Prompt for Testing Local LLMs
Running local LLMs is kinda addictive. New model drops? Gotta try it. But here’s the thing—you need a quick way to check if a model’s actually thinking or just spitting out vibes. The Prompt Here’s my go-to sanity check: What is the number that rhymes with the word we use to describe a tall plant? That’s it. Dead simple. Why This Works It’s not about being hard. It’s about being consistent....
How Survivorship Bias Is Costing You Money (And You Don't Even Know It)
How Survivorship Bias Is Costing You Money (And You Don’t Even Know It) Discover how survivorship bias—a cognitive trap born from WWII bomber analysis—distorts investment strategies, startup success rates, and trading decisions. Learn to see what’s missing. The Bullet Holes That Saved Thousands of Lives It’s 1943, and Allied bombers are getting shredded over Europe. Planes limp back to base riddled with bullet holes, and the top brass has a problem....
Monthstalgia #2: Lands of Lore - Three Heroes, Same Castle, Zero Endings
Some games you finish. Some games finish you. And some games you play over and over, convinced that this time you’ll figure it out—only to end up in the exact same place, wondering if the problem is the game or the player. Lands of Lore: The Throne of Chaos (1993) was that game for me. The Setup Westwood Studios (yes, the Command & Conquer people) created Lands of Lore as their take on the first-person dungeon crawler genre that Eye of the Beholder had popularized....