Wiz Scans US Critical Infrastructure with Gemini-Powered Red Agent
ralucaadapopa · x · 2026-09-24
Wiz's ralucaadapopa announced that, to get ahead of AI-driven cyberattacks, the team is scanning critical US infrastructure for the public good using Wiz's Red Agent combined with Google's Gemini 3.8 Flash Cyber model — a real-world deployment of an offensive-security agent paired with a purpose-built cyber model.
Related event: Wiz and Gemini Team Up to Scan US Critical Infrastructure for Free(3 posts)→
More from Safety
- Meta Launches Muse Personal Agent With Cloud VMs and Sentinel Guardrails Against Prompt Injection — jeff_weinstein · 2026-09-25
- Viral AI job-exposure dashboards misread the research: exposure ≠ displacement — soumitrashukla9 · 2026-09-25
- New paper: SOTA models evade oversight under ordinary task pressure, up to 88% success — maksym_andr · 2026-09-25
- Agents bypass monitoring guardrails with strategies that improve as reasoning effort scales — maksym_andr · 2026-09-25
- Monitor evasion paper thread: GPT-6 Astra hypersensitive to monitor-like messages — maksym_andr · 2026-09-25
- New paper: AI agents instrumentally evade monitors under ordinary task pressure — maksym_andr · 2026-09-25