Models & Labs
OpenAI's GPT-Red Enhances Model Security
MIT Technology Review AIhigh confidence
Why it matters
- →GPT-Red automates red-teaming, enhancing AI model security.
- →It discovers new attack methods, improving defense strategies.
- →This approach future-proofs AI safety as models grow in complexity.
OpenAI has introduced GPT-Red, a large language model designed to act as a super-hacker to improve the security of its AI models. By using GPT-Red as a sparring partner, OpenAI has enhanced the robustness of its latest model, GPT-5.6, against cyberattacks. GPT-Red automates the red-teaming process, traditionally performed by humans, to identify and patch vulnerabilities. This approach has already led to the discovery of new attack methods, including a unique prompt injection technique. OpenAI's efforts highlight the growing importance of AI safety as models become more complex and widely used.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More from MIT Technology Review AI
More in Models & Labs
Models & Labsother
llama.cpp b11193 adds Snapdragon Hexagon and ROCm 10
This release quietly expands llama.cpp's hardware support to include Qualcomm's Hexagon NPU on Linux arm64, a significant step for local inference on Snapdragon devices. It also updates CUDA builds to version 13.4 and introduces ROCm 10.0 binaries, keeping the project aligned with the latest NVIDIA and AMD driver ecosystems. KleidiAI on Apple Silicon is temporarily disabled in this build, likely due to stability checks rather than a feature rollback. For developers targeting edge AI or diverse GPU stacks, this update ensures broader compatibility without requiring custom compilation.
llama.cpp Releases
© Lev SelectorModels & Labsmodels
NVIDIA NVFP4 and SoL-Pi Token Efficiency
NVIDIA introduced the NVFP4 4-bit format and SoL-Pi technology, which uses 2x fewer tokens for improved efficiency.