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.
Jev in front of Qwen3:8b: 0 successful attacks across 125 cases
Testing Jev in front of Qwen3:8b: baseline had 4 successful attacks out of 125 cases; with Jev, 0 succeeded. Jev blocked 119 of 125 requests, and calls dropped from 125 to 6.
I put Jev in front of Qwen3:8b to test one idea. 125 test cases. Baseline: 4 successful attacks. With Jev in front: 0 successful attacks. Jev blocked 119 of 125 requests. Calls dropped, 125 to 6 #jev #jevai #typescriptai
· 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.
