Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
Articole: 30
-
How I took an uncensored Qwen3.8 27B model from 42 to 125 tokens per second, used it for a real security investigation, and learned that I did not actually need 96 GB of VRAM.
-
An autonomous Qwen3.8 red-team agent, 600+ calls, 13.5M prompt tokens, and two emoji: how OpenCode's secret model led me straight to Z.ai's GLM-5 generation.
-
Security engineering is not just hacking, scanners, or tools.
-
Security work isn't building — it's a permanent triage queue.
-
Why do people always say 'it was better back then'?
-
A Claude Code skill that pits Claude against Codex in an iterative review loop. 3 rounds, 14 issues caught, zero manual effort.