Jev and CodeGraph for security review
The typesafe-security-review project combines Jev’s probability judgments with a code graph and OWASP/CWE data for low-cost security scanning.
Independent Evaluation of Jev on AI Security Validation Sets
The author compares Jev with other models on their own AI security validation set, an independent hard benign benchmark, and a third-party hard benign benchmark, concluding Jev is far from bad but not production ready and not air gapped.
Because everybody here is comparing Jev with other models. I compared Jev on our #AISecurity Validation set, a independent hard benign benchmark, and a third party hard benign one. Result: #Jev is far from bad but not production ready. Also not air gapped.
· 0 likesOpen on X
More like this
Jev Delivers 5x Cheaper and More Accurate Security Pipeline Results
A user shares experience using Jev in a security pipeline: over 5x cheaper, faster, and more accurate than smaller, dumber models.
Jev Use Cases and Demo in AI Security
Introduces Jev use cases and a demo in AI security, leveraging its choice-and-probability model with Unity AI Gateway and MLflow integration for safety checks.
