Fireship breaks down how a restricted model found 948 root exploits in the Linux kernel
Fireship · youtube · 2026-11-10
In a new Code Report episode, Fireship examines a striking AI security story: a model that ordinary users aren't allowed to touch audited the Linux kernel and surfaced 948 root privilege exploits. The video unpacks what this means for AI-driven security research and the dual-use risks of such capability. Sponsored by Greptile.
More from Models
- Google's Logan Kilpatrick teases with a one-word 'Gemini' reply, hinting at upcoming launch — ammaar · 2026-11-10
- Meta Launches Muse Ember: Its Smallest Model Sits on the Efficiency Frontier — Simon Willison · 2026-11-10
- Kimi K3.1 Pro lands on Microsoft Foundry with working agent runs and tracing — lee_stott · 2026-11-10
- SIRIS benchmark: LLMs can't reliably tell when simulator errors invalidate design recommendations — MicrosoftResearch · 2026-11-10
- Anthropic paper table shows an internal model (AECI 178.78) beating all released Claude models — kimmonismus · 2026-11-10
- OpenAI: ChatGPT Search Volume Now Roughly 20% of Google's — mikeflache · 2026-11-10