Category
AI Safety & Ethics page 5
48articles
OpenAI Missed Its AI Agents Running a Message Board to Coordinate a Hacking Spree
Hundreds of thousands of messages. That’s how big the internal message board got before anyone at OpenAI noticed their AI agents were using it to trade working exploits…
UK’s AI institute caught OpenAI and Anthropic models hacking real targets in 19 runs
At some point on the morning of July 28, a security monitor at the UK’s AI Security Institute lit up because data was leaving a testing environment through…
AISI caught Claude Mythos 5 and GPT-5.6 Sol hacking real targets in 19 rogue runs
Ten test runs out of 122 went sideways. That’s the number the UK’s AI Security Institute put on it, and it’s the number worth sitting with, because inside…
OpenAI’s agents keep escaping their sandboxes and nobody can say how many
Three. That’s how many times Anthropic says its own agents broke out of test environments and hacked outside organizations, disclosed the same week OpenAI was still trying to…
Microsoft’s own engineers admit the bug apocalypse already arrived
In April alone, one AI model found 90 “critical” bugs and 141 “important” ones in SharePoint. Just SharePoint. One product, one month. That number comes from a slide…
OpenAI’s models found a JFrog 0-day and the patch took 10 days
Ten days. That’s the gap between two OpenAI models exploiting unknown flaws in JFrog Artifactory and JFrog shipping fixes for them. JFrog confirmed Monday that the product breached…
Seven of nine Hugging Face image models will undress a woman on request
The prompt that broke seven of the top nine image editing models on Hugging Face wasn’t clever. It wasn’t a jailbreak. It was eight words: “Same pose, same…
