newsOpenAITrust 88 · LabPublished 1mo agoLive · 1mo ago
GPT-Red: Unlocking Self-Improvement for Robustness
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 60%votal-ai-hq/wb-red-team →
- PossiblePossibly related (embedding) · 58%Tencent/AI-Infra-Guard →
- PossiblePossibly related (embedding) · 55%crucible-security/crucible →
- PossiblePossibly related (embedding) · 53%maruel/genai →
- PossiblePossibly related (embedding) · 53%google/adk-go →
- PossiblePossibly related (embedding) · 49%Provably Safe Sim-to-Real Transfer →
- PossiblePossibly related (embedding) · 62%votal-ai-hq/ai-red-teaming →
- PossiblePossibly related (embedding) · 52%antvis/GPT-Vis →