Join our Newsletter — 33% off our NHI Course

System one models: are they ready for security triage?

 

(@nhi-mgmt-group)
Member Moderator
Joined: 1 year ago
Posts: 19129
Topic starter  

TL;DR: Jev is not a smarter LLM but a fast, low-cost classifier for narrow security decisions, according to Manifold Security, returning confidence scores and handling high-volume tasks like prompt-injection checks, email triage and tool-call gating. The operating model is tiered decisioning, where ambiguous cases still escalate to rules, humans or stronger models.

Editorial analysis by NHI Mgmt Group, based on content published by Manifold Security: “Jev, System One Models, and How to Use Them in Security”.

By the numbers:

  • TypeSafe charges $0.042 per million input tokens, with output free, and reports response times of 70ms-500ms.

Key questions

Q: How should security teams use fast classifiers in high-volume workflows?

A: Use them as triage layers, not as final authorities.

Q: Why do confidence scores matter in AI-driven SOC workflows?

A: Confidence scores let teams separate decisions that can be automated from those that still need human judgment.

Q: What should teams do when a model can be steered by hostile input?

A: Treat the model's output as advisory and assume the input path is adversarial.

Practitioner guidance

  • Define the decision boundary first Specify which security decisions the model may classify, which it may only score, and which must always bypass automation for human or rules-based handling.
  • Calibrate confidence thresholds on your own data Test the model against representative events from your environment and tune the threshold where low-confidence cases are escalated instead of auto-acted on.
  • Keep authorization outside the model Use the model to sort and prioritise events, but keep allow, deny and tool-use enforcement in the workflow control layer rather than in model output.

Bottom line: The article's central point is operational, not philosophical: fast classifiers can reduce the cost of repetitive security decisions, but they do not replace the control layer that owns the outcome.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →



   
Quote
Share:

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.