ed-donner/llm_engineering — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #5926 · UNIT ID 850490697

ed-donner/llm_engineering

Repo to accompany my mastering LLM engineering course

[ JUPYTER NOTEBOOK ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00128

ENGAGEMENT0.81

FRESHNESS1.27

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

3% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

8.43

ACCEL

-0.24

RETENTION

29.7%

PEAK 2026-10-06 · FORK-RETENTION 21.7% · 253 STARS / WINDOW

Author Audience

AUDIENCE

6,534

FOLLOWERS

4,937

OWNER ★

15,967

Engagement Signals

FORKS

7,498

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 253 / 253 (DIVERSITY 1.00)

Why This Is A Finding

ed-donner/llm_engineering собрал 253 звёзд за окно, тогда как у автора всего 4,937 подписчиков — эффективная аудитория ≈ 6,534. Это даёт surprise-индекс 0.00128 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 21.7% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 39% OF 9675 FINDINGS

#260Akun-python/autumn-recruitment[ JUPYTER NOTEBOOK ]0.0653 #414Liuziyu77/Valen[ JUPYTER NOTEBOOK ]0.0361 #969philshiu/Drosophila_brain_model[ JUPYTER NOTEBOOK ]0.0219 #994bicky007/100-python-projects[ JUPYTER NOTEBOOK ]0.0216 #1062PaulamiB-git/solutions-prototypes[ JUPYTER NOTEBOOK ]0.0204

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9675 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 39%

VELOCITY8.433.80+4.63ABOVE 74%

RETENTION29.7%20.3%+9.4 PPABOVE 70%

FORKS7,498138+7,360ABOVE 99%

SURPRISE0.000.01-0.01ABOVE 18%