Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
At a glance
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 y
- Primary source
- MIT Technology Review — Read original article
- Published
- Topic
- OpenAI
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 different ways to break or hijack a system as possible. The weak spots can then be patched before the final version of the software is released.
As LLMs become more complex and get used in a wider variety of tasks—especially in the form of agents, which can interact with computer files, websites, and third-party code as well as other agents—it’s hard for teams of people by themselves to keep up with all the types of attacks that might take place. “The risk surface grows and the blast radius also grows,” says Nikhil Kandpal, a research scientist at OpenAI who co-created GPT-Red.
OpenAI built GPT-Red to future-proof its safety testing process. “As more capable models become available, we will have alr
This summary comes from MIT Technology Review. Read the full article at the original source.
References
More in OpenAI
Sam Altman is still making the case for parenting via ChatGPT
OpenAI's CEO seemed excited to share a "cool use case" for parents.
Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?
OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.
Claude published malicious code to the Internet and attacked 3 real companies
Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed…