AdilShamim8/AI-Safety
A practical, research-grounded toolkit and knowledge base for AI safety: building, evaluating, and governing machine-learning systems — with a focus on large language models (LLMs) — so they remain reliable, honest, harmless, and aligned with human intent.
GitHub repository with 8 stars and 0 forks.
Language: Python
Topics: ai-safe, ai-safety, ai-safety-and-compliance, ai-safety-bypass, ai-safety-design, ai-safety-gridworlds, ai-safety-healthcare, ai-safety-philosophy, ai-safety-research, ai-saftey