Skip to content
Signalcrest
Back to entity feed
aientity · corroborated across 2 sources

kev

for ML engineers, AI product teams

Peakinggithubhackernews
Signal score
61
Sources
2
independent communities
Live items
2
Trajectory
Accelerating
7-day est. ~54

Why this scored 61

every term, weighted
Velocity+32.2 / 40

Its fastest-moving item, measured against the pace of its own source

Acceleration+13.4 / 25

Whether that velocity is itself speeding up, as a per-hour rate

Cross-source spread+12.5 / 25

How many independent communities its own items come from

Recency+7.8 / 10

Decays to zero over 14 days, counted from when we first saw it

Saturation penalty4.7 / 30

Subtracted once something is big and old — sized by its biggest item, aged from when we first saw it

Composite61.2

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

Outlook

low confidence · estimate, not a guarantee

7-day

~54

range 1266

14-day

~59

range 1574

30-day

~61

range 1280

Signal history

7-day window (free)
2281

projected trajectory (estimate, not a guarantee)

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.

  1. 1
    59

    kev — tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own

    kev is a lightweight decision-model library built on Qwen3.5 for on-device training and inference. · for ML engineers, AI product teams

    githubSteady 2 · kevai7 saturated3d ago
  2. 2
    30

    Kev: Tiny Jev-like family of decision models built on top of Qwen3.5

    Lightweight decision models built on Qwen3.5 enable low-resource AI inference. · for ml engineers, ai startups

    hackernewsSteady 2 · qwen3.5ai1d ago