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.
Claude Fable 5 and Kimi K3 compared. What still matters?
Fable 5 remains active as a legacy model and Kimi K3 weights are available. Compare access, context and API costs alongside Fable 5.1 and K3.1 Pro.
LM Studio Bionic. How local is your agent?
Bionic can edit files and run models on your computer, on a second device or in the cloud. What changed in 1.1.10 and how to test your own setup.
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.
Running ChatGPT Sites for a team or a shop
ChatGPT Sites supports WebSockets and sales through payment providers. Check who can publish, how bookings hold up and what hosting is due to cost.
OpenClaw, Hermes or Grok Bot: who gets access to your data?
Three AI agents face the same support case. Compare where tools run, messaging channels, usage allowances and access before connecting a work account.
Five OpenClaw workflows you can test with clear limits
What OpenClaw 2026.10.10 brings to research, browser reconciliation and weekly reporting. Five examples with limited access and results you can check.
Omarchy for AI Developers: What Is Stable and What Is Still a Preview
Omarchy 4.0.6 and the 4.5 preview: what changes for AI developers, which permissions agents receive, and the limits of hardware support, updates and rollback.
Install Omarchy: Stable ISO, Backups and First Steps
Install Omarchy 4.0.6 on x86: verify the download and signature, protect your data, select the right drive, and prepare for updates and recovery.
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.