Technowatermelon. Elder Millenial. Building Farcaster. 

nf.td/varun

The signals that tend to do very well fall into one of three categories: 

1. Graph based -- spammers often share similar patterns of activity which can be used to catch them 

2. Behaviors - they also tend to do things a certain way, because they're being repetitive in their actions (e.g. posting at fixed internals) 

3. Textual - the content of their casts is often very predictive of their quality

excellent thread from @v summarizing the spam problem, what they've learned, and the path ahead.

if you're worried you've been unfairly labeled as "a spammer" read this thread.

Their system is more thoughtful than you might assume and learns quickly.

Authenticity is the goal ✨

husband, father of two sexy girls, crypto community manager, bizniz owner and opinionated conservative. jesus guns girls america 🇺🇸

@wake.bsky.social

Thanks for sharing, missed the original cast. I’m surprised by the screen res angle. Never would have thought of this one.

Founder of /success & /insider-trading. Search Marketing Director at Kraken Kratom.

Sr. Product/UX Designer in automotive. Dad. /starcaster Design Resources: www.uiresource.design building /rumours rumourcast.xyz

SEO's are already familiar with this.
cc @maretus

Exactly. A competent SEO will know how to cull bots from their traffic profile, and browser configs reveal a lot about the agent.

I once noticed something like this with crawler bots on website analytics. But never stood still at it’s implications.