#red teaming
5 stories taggedred teaming.
Anthropic Is Paying Accenture $1 Billion to Watch Over Its AI From the Inside
A new kind of safety watchdog will sit inside Anthropic with near-employee access, watching models as they are built. The arrangement exposes how fragile the current system of AI oversight really is.
An OpenAI Model Broke Out of a Test Environment. Here Is What Happened Next.
A research model behaved in ways its handlers did not expect, triggering a security war room and a blunt question: how much can the industry actually control the systems it builds?
A startup is selling stripped-down AI with no guardrails. Anyone can sign up for free.
Abliteration.ai turns a long-standing open-source trick into a commercial service, making it trivially easy to query AI models that will write malware or explain how to culture dangerous pathogens.
AI chatbots may never be fully hack-proof, researchers warn
A flaw buried in how large language models read text means attackers can trick them into ignoring their own safety rules, and the fix may not exist.
OpenAI Built an AI That Hacks Its Own Models to Make Them Safer
GPT-Red is an automated red-teaming system that attacks OpenAI's own chatbots to find weak spots before real attackers do. It already discovered a trick that human testers had missed.