TrustAI-laboratory/Learn-Prompt-Hacking — GitHub trend

FINDING #383 · UNIT ID 841263635

TrustAI-laboratory/Learn-Prompt-Hacking

This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking course.

[ JUPYTER NOTEBOOK ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0613

ENGAGEMENT0.45

FRESHNESS1.00

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

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

18% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

9.00

ACCEL

+5.61

RETENTION

96.9%

PEAK 2026-08-09 · FORK-RETENTION 50.0% · 63 STARS / WINDOW

Author Audience

AUDIENCE

107

FOLLOWERS

OWNER ★

478

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 63 / 63 (DIVERSITY 1.00)

Why This Is A Finding

TrustAI-laboratory/Learn-Prompt-Hacking собрал 63 звёзд за окно, тогда как у автора всего 59 подписчиков — эффективная аудитория ≈ 107. Это даёт surprise-индекс 0.0613 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 50.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 96% OF 9721 FINDINGS

#66lyogavin/airllm[ JUPYTER NOTEBOOK ]0.18 #184xbsheng/atguigu-note[ JUPYTER NOTEBOOK ]0.0848 #681Morteza-Asadi-Shalmaiy/facial-recognition-pipeline[ JUPYTER NOTEBOOK ]0.0226 #823neoteai/N0-Foundation[ JUPYTER NOTEBOOK ]0.019 #993Lordog/dive-into-llms[ JUPYTER NOTEBOOK ]0.0159

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9721 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.040.00+0.03ABOVE 96%

VELOCITY9.003.43+5.57ABOVE 76%

RETENTION96.9%32.1%+64.7 PPABOVE 99%

FORKS48130-82ABOVE 28%

SURPRISE0.060.01+0.05ABOVE 92%