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 security questionnaire response classification evaluation and tuning
The post discusses Jev's performance in categorizing security questionnaire responses (implemented, N/A, not implemented), comparing with Claude, noting that Jev needed tuning for more accurate results.
#Jev security questionnaire response categorization (implemented, N/A, not implemented) given the question+response then a ground truth eval. - Claude initially performed better with little direction - Jev questions needed tuning to provide a more accurate response. Once tuned,
· 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.
