Tag

#ai safety

4 articles

Inside our approach to the Model Spec

Learn to build a practical model specification framework that balances AI safety, user freedom, and accountability, similar to OpenAI's approach.

Mar 2512

OpenAI open-sources teen safety policies for developers amid mounting lawsuits over ChatGPT deaths

Learn to build a basic AI safety monitoring system that detects potentially harmful content, similar to OpenAI's teen safety policies. This beginner-friendly tutorial teaches you how to implement keyword detection, sentiment analysis, and safety violation handling.

Mar 244

3 ways Cisco's DefenseClaw aims to make agentic AI safer

Learn to build a basic agentic AI monitoring system that demonstrates the core concepts behind Cisco's DefenseClaw, which aims to make enterprise AI safer through orchestration.

Mar 235

Reasoning models struggle to control their chains of thought, and that’s good

Learn how to implement Chain-of-Thought prompting techniques using Hugging Face Transformers to guide language models toward more structured reasoning patterns, similar to OpenAI's CoT-Control research.

Mar 724