agent-security

Tag

Cards List
#agent-security

Continuously hardening ChatGPT Atlas against prompt injection

OpenAI Blog · 2025-12-22 Cached

OpenAI announces security hardening of ChatGPT Atlas against prompt injection attacks through adversarial training and strengthened safeguards, including a rapid response loop for discovering and mitigating novel attack strategies before they appear in the wild.

0 favorites 0 likes
#agent-security

How we contain Claude across products

Anthropic Engineering · 2026-05-26 Cached

Anthropic discusses how they contain Claude across products by capping blast radius through containment architectures and reducing human supervision fatigue, sharing lessons from deploying Claude.ai, Claude Code, and Claude Cowork.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback