Written by Philipp on 2026-08-12
Open-Weight LLMs: Making the Right Choice
AICloud models are convenient. They are also expensive, dependent on US providers, and often bound to rate limits. The debate has intensified in recent weeks. Frontier models with open weights now reach a quality that until recently was reserved for closed cloud APIs. On Oxide and Friends, Simon Willison speaks of an “Open Weight Revolution.”
Written by Philipp on 2026-07-22
Tailscale VPN: Connect Your Own Services on Your Own Infrastructure
AI . Network . Personal . Security . ToolingProxmox in the data center, a laptop in the home office, a Raspberry Pi at the edge of a field, and a DGX Spark for inference: your own hardware is rarely in one place. NAT, firewalls, and dynamic IPs separate the devices. Manual WireGuard means: exchanging keys, maintaining IPs, updating firewall rules. Tailscale builds on
Written by Philipp on 2026-07-01
Token Governance for LLMs: Why Shared Budgets Fail (and How to Do It Better)
AI . PersonalYour team shares a GitHub Enterprise account. Copilot is enabled for everyone. A shared budget, no individual limits, no visibility into who consumes what: “it’s in the budget.” Then, in mid-June 2026, GitHub switches its billing from Premium Request Units to token-based billing. Suddenly the budget is no longer “unlimited”. The error message arrives faster
Written by Philipp on 2026-03-17
Prompt Engineering Is Dead. Long Live Context Engineering.
AI . PersonalI stopped optimizing my prompts. Not because it doesn’t work – but because it’s the wrong question. The right question is: What’s in the context when the agent starts working? The Problem with Long Conversations Anyone who works regularly with LLMs knows the pattern: at the beginning of a chat, everything runs smoothly. After twenty,
Written by Philipp on 2020-06-08
Securely Connected Remote Work
AI . Network . Personal . Security . ToolingConnecting Distributed Nodes with a Nebula VPN Remote work has become the norm in the current situation. In a digital working environment, this should actually offer optimal possibilities. But one thing can become a problem: essential systems required for the daily workflow often cannot be used in a remote-work context. Not every company has set