Chris Choquette-Choo

mentions 2 type Person feed RSS

// recent coverage 2 mentions

21:49

2026-07-15

thenextweb.com

artificial-intelligence

OpenAI built an AI super-hacker to break its own models, then locked it away

OpenAI has built GPT-Red, an automated red-teaming model that hunts for security flaws in its own AI systems, and will not release it due to safety concerns. In tests, GPT-Red cracked 84% of attack sc…

17:09

2026-07-15

technologyreview.com

artificial-intelligence

Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer

OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their defenses against cyberattacks. Last week the company released the latest ver…

// co-occurs with top 8 entities

OpenAI 2 GPT-Red 2 GPT-5.6 2 Jessica Ji 2 Nikhil Kandpal 1 Dylan Hunn 1 Georgetown University's Center for Security and Emerging Technology 1 Andon Labs 1

// topics top 6 topics

artificial intelligence 2 ai safety 2 ai research 2 large language models 1 ai products 1 ai agents 1