KI-gestützte Schwachstellenforschung: Wenn Offensive auf Automatisierung trifft🇬🇧 Read in EnglishAugust 15, 2026~6 min readDevOpsSecurityai-securityvulnerability-researchoffensive-securityglm-5.3gpt-5.6-cyberdevsecopsgraph-security
August 18, 2026· ~8 min readRunning a 27B Hybrid SSM Model with 128k Context on a 12 GB Laptop GPUBenchmark: Qwen3.8-27B with hybrid attention/SSM architecture on RTX 4080 Laptop. 19% prefill degradation over 64x input, constant 2.76 tok/s generation, and 128k context in 8.8 GB VRAM.
August 16, 2026· ~6 min readk3s Disaster Recovery Testing und Edge-PatternsUmfassende DR-Tests und edge-spezifische Patterns für k3s — Failover-Validierung, geplante Snapshots, Multi-Cluster-Recovery sowie RPO/RTO-Planung.
August 15, 2026· ~4 min readAI Model Supply Chain Security: The LiteLLM Incident and What It RevealsMalicious LiteLLM releases tied to a Trivy hack may have exposed 2,100+ organisations. The AI model supply chain has the same weaknesses as the npm supply chain — and worse, because models are opaque. Here's the threat model and the defensive stack.supply-chainai-securitylitellm