Clint Josy is an AI security researcher and leader. Offensive security, exposure management, and AI-driven defense, written up plainly. OSCP, CRTO, CHFI.https://clintjosy.pages.dev/https://clintjosy.pages.dev/blog/2026-05-01-your-ai-your-rules-running-a-local-llm-with-gpu-acceleration-on-proxmoxhttps://clintjosy.pages.dev/blog/2026-05-01-your-ai-your-rules-running-a-local-llm-with-gpu-acceleration-on-proxmoxFrom 3 tok/s frustration to 21 tok/s GPU-hybrid inference - a real engineer's guide to self-hosted...Fri, 01 May 2026 00:00:00 GMTllmselfhostedproxmoxnvidiahttps://clintjosy.pages.dev/blog/2026-04-23-openmythos-teardown-dissecting-the-open-source-reconstruction-of-claude-mythoshttps://clintjosy.pages.dev/blog/2026-04-23-openmythos-teardown-dissecting-the-open-source-reconstruction-of-claude-mythosA deep technical dissection of OpenMythos - the community-built Recurrent-Depth Transformer that claims to reverse-engineer Anthropic's Claude Mythos. We crack open the architecture, every novel mechanism, the training pipeline, and the security implications of locally-runnable frontier reasoning models.Thu, 23 Apr 2026 00:00:00 GMTmachinelearningdeeplearningsecurityopensource