Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Safety & Guardrails
/
Output Guardrails
Output Guardrails
Subtopic
2 questions
Questions tagged with Output Guardrails — part of Safety & Guardrails.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Why run a toxicity classifier on output even when the model was RLHF-tuned to refuse harmful content
Flashcard
Easy
·
Qual 4.0
Anthropic
OpenAI
Pick the right reaction when an output guardrail detects a phone number the model just emitted
Multiple Choice
Easy
·
Qual 4.0
Microsoft
Anthropic