Rethinking security engineering with Jev
X post arguing that purely engineering decisions in security work belong to Jev rather than to a chat model.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is a post on X by a security practitioner. According to the directory summary, it argues that decisions in security work that are purely engineering judgments (narrow, typed calls with a fixed set of outcomes) are better handled by Jev than by a chat model.
No thread text was fetched, so the examples and any measurements behind the argument are not available here. The point fits a recurring theme in the Jev community: keep generative models for open-ended analysis and use a decision model for the high-volume, bounded triage calls in between.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Which security engineering decisions should be delegated to a decision model?(inferred) | — |
How it works
- Identify bounded engineering judgments in a security workflow
- Route them to a decision model instead of a chat model
- Keep open-ended analysis with the LLM
Strengths
- Frames where a typed decision model fits in security work
Caveats
- Opinion post; grounded only in a one-line summary
- No data or code
At a glance
- Type
- Discussion
- Status
- discussion
- Has code
- no
- Has tests
- no
Use cases and integrations
How curated lists describe it
X: argues that purely engineering decisions in security work belong to Jev rather than a chat model.
yibie/awesome-jev
Frequently asked questions
What does the post argue?
That purely engineering decisions in security work belong to Jev rather than a chat model.
Is there code?
No, it is a discussion post.
Where is it?
On X at x.com/Kostastsale/status/2100362415187833048.
Related projects
Auto-updated bilingual leaderboard of Jev ecosystem projects, tutorials and discussions, discovered daily and sorted by GitHub stars.
ProjectproductionChatGPT-style web chat where every word of every reply is a Jev multiple-choice decision over a ~1,800-word vocabulary plus END.
ProjectprototypeTypeScriptGallery of small Python demos where Jev answers typed questions on realistic state and explicit policy decides the action or fallback.
AppprototypePythonExperiment that deliberately misuses Jev as a text generator by asking which symbol comes next and sampling from the returned distribution.
ProjectresearchPythonChat client that makes Jev write by asking Next word? over a 20,000-word dictionary in 255-word buckets plus a run-off.
ProjectresearchPythonIssue in the Orcha multi-agent orchestration project proposing to move judgment calls onto Jev to cut model cost.
ProjectdiscussionPython