Technology · 3 views
Security researchers used Claude to help them hack into OpenAI
A three-person team of researchers used a corrupted image file and forum software to hack into OpenAI.
Technology 
Story intelligence
Coverage Single outlet Single-outlet story
Views 3 Community interest
Brief read Under 1 min brief 35 words
AI Summary
A trio of independent security researchers from Hacktron reported that they breached OpenAI employee accounts in under 72 hours. The intrusion was carried out using Anthropic’s Claude Opus 4.8 and Claude Opus 5 language models.
AI summaries can be wrong sometimes—always verify important details using the source article.
How AI & Automation are usedMore from Technology
Continue reading recent Technology coverage
- What Hollywood thinks about existential AI warningsContinue reading
- iOS 27.2’s First Developer Beta Brings These Features to Some iPhonesContinue reading
- An Undercover Google Analyst Infiltrated a Notorious Supply Chain Hacking GangContinue reading
- Breville’s Wild New Toaster Swaps the Timer for Optic Sensors to Tell When Toast Is DoneContinue reading
Support HappeningNow
Independent AI-powered news analysis is reader-supported. Your contribution helps cover infrastructure, summaries, and continued platform development.
Support HappeningNow