So, yeah, apparently part of wrapping my head around nostr will have to include understanding bot behavior. Hence the cat pictures bot thinks I want to zap it. Nah. My initial assumption was that these bots are using natural language processing for targeting. ChatGPT thinks “…sometimes yes, but usually it’s much dumber than that.” Further, it says: When a bot follows you, probability-wise: ~70–80%: dumb follow-spray ~15–25%: keyword trigger ~5–10%: graph-based <1%: real NLP targeting So the m.o. for follow-spray purportedly is Subscribe to recent kind:1 notes on 5–20 popular relays. Extract pubkeys from: • Anyone who posts • Anyone who replies • Auto-follow them And the m.o. for keyword-trigger purportedly is Subscribe to kind:1 notes with keyword filters • Simple string matching or regex • Follow authors whose posts contain keywords

🤔 So wait… was it the earlier post referencing my cats, or was it my mention of AARP that caused the astrology bot to glom on to my account? Drats…pigeon-holed again.