AI
Models & tools
Which model for which job – and does it really have to be the cloud? These articles compare models, tools and setups soberly: capabilities, costs, privacy.
Fable 5 vs. Kimi K3: The New Top Duel in AI Models
Claude Fable 5 versus Kimi K3 – and the rest of the field: strengths, prices, context windows and benchmarks of today's frontier models, soberly compared. As of July 2026.
Local AI vs. Cloud: When Your Own Models Pay Off
Local AI vs. cloud compared: data sovereignty, costs under sustained load, a worked payback example, and the routing pattern that combines both worlds.
AI PCs and NPUs: What's Really Behind the Marketing
“AI PC” is stamped on almost every new laptop. What NPUs actually do, which specs matter when buying – and when waiting for the next generation pays off.
Open-Weight Models: What “Open” Really Means in AI
Open-weight vs. open source in AI: the three levels of openness, a licence comparison, the most common mistakes, and a checklist before deployment.
Understanding AI Costs: Tokens, Context, Caching
Understanding AI API costs: the three pricing factors behind every bill, a worked example, and the five practical levers that keep costs under control.
Why AI Hallucinates – and What Actually Helps
Why does AI hallucinate at all? The mechanics behind invented facts, a worked example, the ranked countermeasures, and a checklist for the practical check.