💻 Technology 2d ago · Will Douglas Heaven

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

MIT Technology Review
Authoritative reporting on emerging technologies
View Channel →
Source ↗ 👁 0 💬 0
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 version of its flagship LLM, GPT-5.6. OpenAI says that training it against GPT-Red made the model its most robust release yet.





GPT-Red automates a type of safety evaluation for software systems known as red-teaming, which is typically done by a team of human testers. The aim is to find as many dif

Comments (0)

Sign in to join the discussion

More Like This

Nvidia launches Cosmos 3 Edge model and expands its physical AI push in Japan
SiliconANGLE · 18h ago
Verizon shedding stores signals a shift in the way the carrier does business
Android Police · 18h ago
Why Apple Sued OpenAI, New York Takes on Data Centers, and What to Know about Cyclosporiasis
WIRED · 18h ago
TSMC boosts Arizona fab investment by $100B after strong second quarter
SiliconANGLE · 18h ago
China Just Dropped Another Bomb on America’s Frontier AI Companies
Gizmodo · 18h ago
My favorite Obsidian alternative isn't Logseq or Joplin, it's a block-based app that's actually more private
XDA · 19h ago