1 repo
Awesome GitHub RepositoriesArtificial Intelligence Safety
Frameworks and defensive strategies aimed at mitigating bias, adversarial attacks, and unsafe behaviors in AI.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Artificial Intelligence Safety. Refine with filters or upvote what's useful.
Awesome Artificial Intelligence Safety GitHub Repositories
We'll search the best matching repositories with AI.
- dair-ai/Prompt-Engineering-Guide
This project is a comprehensive educational resource and knowledge base dedicated to the development and application of large language models and autonomous agentic systems. It provides a structured framework for understanding prompt engineering, context management, and the architectural patterns required to build task
MDXagentagentsai-agents
Explore sub-tags
- Adversarial Behavioral PatternsPhenomena where language models exhibit unintended or contradictory personas and behaviors based on training data dynamics.
- Algorithmic BiasesTechniques for identifying and reducing discriminatory or skewed outputs in generative models.
- Defense TacticsTechniques and strategies implemented to protect language models against adversarial inputs and prevent the generation of harmful or biased content.
- System Prompt Guardrails