Pasting a Claude or DeepSeek API key straight into your code "just to test it quick" leaves a trail in your git history and your logs. A no-nonsense guide to environment variables, rotation, and what to check before sharing a repo.
Sep 09 2026 · 7′ · Tutorials · nextjs · anthropic
DeepSeek Reasonix shows up as a native coding agent with aggressive caching and low cost. Before you adopt it or dismiss it, there's a more useful question: what specific problem does it actually solve in a real stack, and what reproducible experiment confirms that?
Sep 03 2026 · 9′ · Opinion · LLM · ia
Cline can create files, run commands, and open the browser autonomously from inside VS Code. That sounds like productivity. It also smells like risk if you haven't thought through the permissions before you start. My thesis: the mental model matters more than the tool.
Aug 17 2026 · 9′ · Tutorials · TypeScript · LLM
DeepSeek's API is compatible with the OpenAI SDK — that makes the integration almost trivial. The real problem isn't the plumbing. It's deciding whether the model is actually worth it for your use case, without buying the hype or dismissing it out of fashion. Here's the framework.
Jul 22 2026 · 8′ · Tutorials · TypeScript · nextjs
Running the OWASP LLM Top 10 as a real audit is a completely different experience than reading it as a checklist. I ran it against my TypeScript agent stack with system prompts, MCP tools, and Cline — and the findings were uncomfortable.
Jun 20 2026 · 9′ · Tutorials · TypeScript · LLM
The homelabber community is building local AI dev platforms and the discussion is genuinely interesting. I have some observations that go beyond the initial excitement — and a checklist so you can decide whether the experiment is actually worth it.
Jun 16 2026 · 9′ · Opinion · TypeScript · LLM
A municipality announces its "own" LLM and the technical community discovers it might be a merge of an existing model. My read: the real problem isn't the fraud — it's that almost nobody knows how to verify it. Here's the checklist.
Jun 15 2026 · 9′ · Opinion · LLM · open source
The most common mistake when implementing MCP tools is coupling them to the provider's SDK. The spec exists to prevent exactly that. A practical architecture guide: the input/output contract that makes a tool work across Claude, GPT, and local models without rewriting anything.
Jun 10 2026 · 8′ · Tutorials · TypeScript · LLM
A system prompt isn't documentation for the model — it's a contract. After several redesigns, I landed on a format with fixed sections, explicit limits, and dynamically injected context. Here's what survived and why.
May 29 2026 · 9′ · Tutorials · TypeScript · produccion
Architecture, real systems, product decisions and technical lessons. Everything reviewed with my own judgment before it ships.
230 articles published