Continuously hardening ChatGPT Atlas against prompt injection

OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning.

From the source
OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning.
openai.com

Visit source ↗openai.com

Announced

Other stories

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot weekly releases — August 24Capability change

Amazon · 28 AugSpreading the load: How Salesforce met Multi-AZ HA with SageMaker Inference ComponentsCapability change

OpenAI · 28 AugOur decision on Cursor following its acquisition by SpaceX

22 Dec 2025 00:00 UTC

Detected

03 Aug 2026 21:11 UTC (+224d after)

OpenAI · 28 AugSupporting Thailand’s next generation of AI startups

Partnership

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South LanguageCapability change