One idea, two cosmic mysteries—linking Little Red Dots and globular clusters

A new study led by astronomers at The University of Texas at Austin proposes a theory that could solve two astronomical ...
Decrypt

OpenAI Uses AI Red Team to Strengthen GPT-5.6 Against Prompt Injection Attacks

OpenAI introduced GPT-Red, an automated AI system designed to find vulnerabilities in GPT models before release. The company said GPT-Red was used to train GPT-5.6, reducing failures on one of its ...
The Hacker News

OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol

OpenAI says GPT-Red automates prompt injection testing and helped GPT-5.6 Sol record sixfold fewer direct injection failures ...
MIT Technology Review

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 ...

You can use altered images to trick AI systems, Florida study shows

Florida International University researchers found AI can be tricked with altered images, which can identify risks in the ...