jev
for platform engineers, devops teams
Why this scored 0
every term, weightedIts fastest-moving item, measured against the pace of its own source
Whether that velocity is itself speeding up, as a per-hour rate
How many independent communities its own items come from
Decays to zero over 14 days, counted from when we first saw it
Subtracted once something is big and old — sized by its biggest item, aged from when we first saw it
Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On an entity's first sighting there's no previous reading to compare against, so acceleration starts from a neutral prior rather than a measurement, and velocity falls back to engagement over its whole lifetime until a second reading exists. Full methodology
Signal history
7-day window (free)The evidence
The live items this entity's score aggregates — every community independently talking about it right now. This is the corroboration, shown, not claimed.
- 151
Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers
Jev decision models lag behind LLM judges and classic classifiers, limiting their utility. · for AI engineers, ML researchers
hackernewsHeating 3 · jevai28d ago - 249
Jev-powered autocorrection
Jev library provides autocorrection in editors, reducing manual text-processing effort. · for editor plugin developers, devs
lobstersSteady 4 · jevdevtools41d ago - 342
How to Use Jev: A practical guide to TypeSafe's System One model
Guide shows how to apply Jev's System One model for type-safe AI pipelines. · for ml engineers, data scientists
devtoSteady 3 · jevai44d ago - 441
Jev After Eight Days of Independent Tests: Level With Mid-Price LLMs, Behind the Frontier
Jev matches mid-price LLMs but trails leading models, indicating competitive performance limits. · for ml engineers, ai researchers
devtoSteady 4 · jevai39d ago - 539
Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences
Jev evaluates semantic choices for scientific decision-making. · for scientific researchers
arxivSteady 5 · jevscience41d ago - 639
Decision-Oriented Recommendation Reranking: An Empirical Study of Jev
Study shows Jev improves recommendation reranking accuracy. · for recommendation engineers
arxivSteady 5 · jevai32d ago - 738
I Put Jev Behind a TLA+ Spec and Ran 1,680 Chaos-Tested Pharmacy Decisions. Zero Wrong Verdicts.
TLA+ verification shows Jev makes zero wrong pharmacy decisions in chaos tests. · for reliability engineers
devtoSteady 5 · jevdevtools44d ago - 837
Jev in Medicine: A Benchmark Evaluation. Preliminary Results
Benchmarks the Jev model for medical applications with preliminary results. · for medical AI researchers
arxivSteady 4 · jevscience34d ago - 937
Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding
Compares JEV and LLMs on legal documents, highlighting decision differences. · for legal tech developers
arxivSteady 5 · jevai39d ago - 1037
Language models for text classification: From bag-of-words to Jev
Introduces Jev model for text classification, offering a new approach beyond bag-of-words. · for ml engineers, data scientists
hackernewsSteady 4 · jevai33d ago - 1135
A single function Jev-like wrapper for LLMs, including vision models
Provides a minimal wrapper to call LLMs and vision models with a single function. · for AI integration engineers
hackernewsSteady 3 · jevai37d ago - 1235
I turned Jev into a (lousy) chatbot
Converted the Jev library into a basic chatbot, demonstrating rapid prototyping of conversational agents. · for devs experimenting with LLMs
hackernewsSteady 4 · jevai42d ago - 1335
Valid Schema, Wrong Content: Using Jev to Guard a Google ADK Agent
Jev validates schemas but cannot ensure content correctness for Google ADK agents. · for cloud engineers
devtoSteady 2 · jevdevtools44d ago - 1435
This week I made a mutual-aid app using Sanity and Jev
Shows how to build a mutual-aid app using Sanity CMS and Jev library. · for full-stack developers
devtoSteady 3 · jevdevtools31d ago - 1535
kicking the tires on jev (TypeSafe's System One model) with 2048
TypeSafe's System One model (jev) now supports 2048-token context for AI game applications. · for ml engineers
lobstersSteady 3 · jevai44d ago - 1635
Introducing System One Models & Jev
Launches new AI models, giving developers fresh capabilities for integration. · for ml engineers, data scientists
lobstersSteady 3 · jevai46d ago - 1735
Jev vs Claude: Who Wins?
Jev vs Claude comparison helps teams pick the right LLM for TypeScript workloads. · for ML engineers, dev leads
devtoSteady 3 · jevai45d ago - 1835
JEV vs. LLMs as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places
Compares Jev and LLMs as rubric judges, noting speed and cost trade-offs. · for ml evaluators
arxivSteady 4 · jevai38d ago - 1934
How to Moderate Live Chat in Real Time with Jev and Composio (Discord + Twitch)
Shows how to add real-time moderation using Jev and Composio for chat streams. · for platform engineers, community managers
devtoSteady 3 · jevai33d ago - 2033
Turning GLM-5.3-Flash into a Jev-like decision model
Adapts GLM-5.3-Flash for decision modeling, useful for ML engineers building inference pipelines. · for ml engineers, ai product teams
hackernewsSteady 3 · jevai36d ago