Kernel Recipes 2026 - Security in the LLM age
Kernel Recipes · 2 位 HN 用户推荐 · 2026–2026
Notice how his praise for the tools differs from so much of the expressed positive sentiment for said tools here on HN. The "low-horsepower" people I've known tend to praise things in a way that smells very much like astroturfing. The "high-horsepower" people I've known both express very nuanced opinions and tend to know better than to burn a ton of time squabbling with Internet Randos in a place
— simoncion, 2026The bots make mistakes all the time, even through multiple rounds of reviews. Thus I have zero faith that they will produce secure code reliably 100% of the time. More Ai does not magically fix this, they go down the wrong path and double down, or work around incorrect assumptions. This is a good talk by a member of the Linux security team: [link]
— verdverm, 2026