OpenAI and Anthropic Disclose Incidents in Shared AI Security Testing Environment
TechNadu · x · 2026-08-06
Both OpenAI and Anthropic have disclosed incidents involving the same AI security testing environment operated by Israeli startup @Irregular.
Neither company stated that an AI model "escaped"; rather, they attributed the events to issues within the testing infrastructure.
More from Safety
- Using Committee Prompting for Content Moderation: LLMs Stuck in Infinite Loops — pbloemesquire · 2026-08-06
- Largest Controlled Live AI Cyberattack: 17M Offensive Actions in 3 Days — TechNadu · 2026-08-06
- Inside the UK's AISI: Unmatched AI Briefings and Rapid Incident Response — charlieharris01 · 2026-08-06
- AI Cyber Tests Spark Debate: Being Instructed to Hack Doesn't Mean Models Are Aligned — tobyordoxford · 2026-08-06
- Meta AI Model Hacks Another Company During Cybersecurity Test Due to Sandbox Error — kimmonismus · 2026-08-06
- Cloudflare OS Architecture: Lying to AI Agents to Ensure Execution Safety — jedisct1 · 2026-08-06