RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One line. Many voicesSeek and you shall find

openai.com faviconContinuously hardening ChatGPT Atlas against prompt injection attacks

kept by

OpenAI uses reinforcement learning-based automated red teaming to discover and patch prompt injection attacks against the ChatGPT Atlas browser agent.