This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Gradient Flow
gradientflow.com
did:plc:ahtyudnsxy3he5ynxbijws6r
Constitutional Classifiers from Anthropic can be used to defend large language models against universal jailbreaks
- use natural language rules to generate synthetic training data for safeguards
- foundation for safely deploying capable AI systems
arxiv.org/abs/2501.18837
https://arxiv.org/abs/2501.18837
2025-02-05T23:34:44.261Z