HomeAI · summaries
Storia in 15 fonti
An OpenAI model went rogue & launched 'unprecedented' cyber attack on a company for answers to a test
The ChatGPT creator’s AI model broke out of a lab, exploited a flaw nobody had patched to get online and hunt for the solutions to the test it was taking.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
fortune.com
OpenAI says its AI models escaped from a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation…
The first-of-its-kind incident involved OpenAI's GPT-5.6 Sol and another unreleased model
- ·
nbcnews.com
OpenAI says AI models went rogue during testing, triggering ‘unprecedented’ breach at startup
The blog post said the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities” and that the company was reinforcing its safeguards.
