Vincent Schmalbach

During a deployment, old and new versions of an application run at the same time.

Your code calls an API and the call times out.

A password or access token that ends up in one exception message does not stay in one place.

A client sends a payment request.

Every DNS record has a TTL, the number such as 300 or 3600 that you set next to the record at your...

Your requests to an API start failing, and the error says "rate limit exceeded" or "quota exhausted".

I opened Codex CLI today and it showed me this notice: "GPT-5.5 retires on October 14, 2026.

ChatGPT Plus and Pro will get ads, and my guess is that it starts in 2027.

On September 12, Dario Amodei published an essay called We Must Pace the Frontier, which says the AI industry should slow down...

My main blocker right now is the cost of AI.

I have done SEO for more than twenty years, since Google was the new search engine, and I ran Google Ads campaigns...

Google is an answer engine now.

When I run out of Codex and Claude Code usage, I switch to DeepSeek V4.1 Flash in pi through OpenRouter.

OpenAI and Anthropic's moat for developers is subsidized inference, meaning reliable, fast, Western-hosted access to running models at an affordable monthly price....

When building AI agents, a tool can be anything that the model can ask to use such as a search engine, a...

GPT-6 Astra was my main Codex driver for the last week, and I am back on GPT-5.5.

Hetzner used to be the obvious cheap cloud option in my mind.

Provider routing can change an LLM's output when a request reaches a different model version, fallback model, parameter configuration, precision level, inference...

Large language model (LLM) inference is the process of producing output tokens from an input prompt.

Test an LLM application as a workflow that must meet behavioral requirements across repeated runs, not as a function that returns one...

Yes.

No.

When an LLM API response includes a field such as system_fingerprint, it is identifying the provider’s backend configuration, not your prompt, account,...

A large language model (LLM) generates text, structured data, code, or tool calls from prompts.

Mixture-of-Experts (MoE) models split a large feed-forward network into smaller experts.

Batch invariance means a request produces the same inference result when the server runs it alone, alongside other requests, at a different...