Red Teaming

8 posts · 5 sources

LangChainYouTube6d

Building Engine v2: How LangChain approaches agent improvement

DataRobotBlog4w

Adversarial evaluation for Agent Assist: ship agents that survive production

AnthropicBlog24 Nov

Mitigating the risk of prompt injections in browser use

AnthropicBlog21 Jun

Agentic misalignment: How LLMs could be insider threats

AnthropicBlog22 Aug

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

MetaBlog20 Jul

How Meta and the security industry collaborate to secure the internet

GitLabBlog29 Jan

You asked, and our Red Team answered

GitLabBlog12 Feb

Google Cloud privilege escalation & post-exploitation tactics