Tags

• Metadata: #topic
• Part of: OpenAI [[DeepMind]] [[Anthropic]] Artificial intelligence safety
• Related:
• Includes:
• Additional:

Significance

Intuitive summaries

Definitions

• Form of evaluation that elicits model vulnerabilities that might lead to undesirable behaviors. The goal of red-teaming language models is to craft a prompt that would trigger the model to generate text that is likely to cause harm

Technical summaries

Main resources

• Red-Teaming Large Language Models

Landscapes

Contents

Deep dives

Brain storming

Additional resources

Related

Related resources

AI

Additional metadata

• processed #processing #toprocess #important #short #long #casual #focus

• Unfinished: #metadata #tags