Warpcast Spam labels are improving 

Our new system uses LLMs to make better decisions. It will make fewer mistakes in both directions and will prevent legitimate users from getting the spam label. 

We expect fewer users to get the spam label as a result of this change. It may take a few weeks to roll out fully.

Technowatermelon. Elder Millenial. Building Farcaster. 

nf.td/varun

What makes a user spammy? 

There are many signals of inauthentic activity. Doing one or two of these will not get you the spam label, but doing many will. 

- profile that is clearly automatically generated with no effort put in 

- posting content from the internet and pretending it is yours 

- using ai to automatically post messages for you 

- replying and mentioning many users who never interact with you or follow you 

- posting and resharing repetitive content, just like a bot might 

- operating in rings, where accounts coordinate to like or boost certain accounts 

- casting, following, liking or resharing things in an automated fashion to artificially get others to follow you 

- impersonating well known accounts on the network 

- getting muted or blocked by many other users on the network

What’s changing? 

- labels are now binary instead of a three point scale. They will be either “likely to be spammy” or “unlikely to be spammy” 

- our new models use llms to look at profiles and check for inauthentic behavior 

- they also factor in verifications and many new signals to get more accurate

i wanted to make a joke with an automatically generated general llm response but it looks like accounts that do this for living beat me to it

can i try to understand better, so trying to get others to follow you by posting content that’ll resonate with them more is regarded as spammy? (in short trying to gain followers) 

if so how does one try to compete with the already boosted warpcast accounts that didn’t organically acquire 100k+ followers ?

Repetitive content because mini apps will ask you to share on a daily basis to gain points on their leaderboards, and also to bring more people to use their mini apps. This is part of the Farcaster ecosystem, so why should it be considered "spammy behaviour"????? @v

Getting spam labels is worse than a breakup.
@escanorl

Nice, can't wait!

Btw Today a lot/some of the mistakes(?) are also caused by manual inputs and I assume those do still exist? Manual inputs make legitimate users stuck on label 1 forever. Maybe they did do something bad in the past and deserved it idk but I do think they should expire and we should show additional info about the why. Feels like manual inputs are a bit closers to nerfing

This is great! 👍 
I wonder if my MiniApps activity will be considered spam? 
I'm worried.

Varun. Pardon my ignorance, what is LLMs?

Great!
Will we see changes in the structure of the spam.jsonl file?

This seems to be helpful 
Hi @munadefi 

Let watch it for spammers

I love this - are you all using an out of the box solution or opting to train the models yourselves?

Spam rules tighter than other free platforms😪.
It is not fair.

You mentioned tagging people who don't follow you.
How then can we get their attentions?
Especially we small accounts?

I got blocked yesterday cuz they thought I was transphobic, does that count as being spam ?

Onchain Entrepreneur 
SausageDad the Memelord
Creator of /memelords and /artlords

this is hella good news for many creators!! @sausagedad check this out!!!

whats the best way to see what label your account has?