technique

human red teaming

techniqueactivehuman-red-teaming-70cfc900·1 events·first seen 28d ago

Aliases: human red teaming

Co-occurring entities

More like this (12)

automated red teaming red-teaming AI-assisted red teaming OpenAI Red Teaming Network Anthropic Policy Frontier Red Team human-in-the-loop pattern Red-Teaming Resistance Leaderboard humanlayer/12-factor-agents human uncertainty alignment Frontier Red Team adversarial training HumanEval

Recent events (1)

6Openai Blog·28d ago·source ↗

Advancing Red Teaming with People and AI

OpenAI published a blog post describing advances in their red teaming methodology, combining human red teamers with AI-assisted approaches. The post outlines how AI tools are being integrated into the red teaming pipeline to improve coverage and efficiency of safety evaluations. This represents an evolution in OpenAI's pre-deployment safety testing practices.

Evaluation and Benchmarking AI Safety Research AI-assisted red teaming OpenAI human red teaming +1 more