Signalcrest
← Back to feed
hackernewsai

Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it

Censorship not transferred

Steady

11

signal score

🔗 2

sources · deepseek

Cooling

7-day est. ~6

Why this scored 11

every term, weighted
Velocity+3.0 / 40 max

Engagement per hour, normalized against the fastest item on its own source

Acceleration+0.0 / 25 max

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

Cross-source spread+2.8 / 25 max

How many independent communities are talking about the same entity

Recency+8.1 / 10 max

Decays to zero over 14 days

Saturation penalty2.6 / 30 max

Subtracted once something is big and old — we rank what's next, not what's peaked

Composite11.3

Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On a topic's first sighting there's no previous reading to compare against, so acceleration starts from a neutral prior rather than a measurement. Full methodology

Outlook

low confidence · estimate, not a guarantee

7-day

~6

range 39

14-day

~4

range 08

30-day

~3

range 08

Signal history

7-day window (free)

— — projected trajectory (estimate, not a guarantee)

Entities

gptossdeepseek
Embed a live signal badge
Signalcrest signal badge
[![Signalcrest signal](https://www.signalcrest.app/api/badge/hn%3A49113599)](https://www.signalcrest.app/topic/hn%3A49113599)

Drop this in a README or blog post — it updates automatically as the score moves.