Farcaster

Top interactors (by number of trending casts interacted with):
(trending in this cases means in the trending feed)

1. ndyy (FID 884066) — 168 casts (Likes: 168, Recasts: 0, Replies: 1)
2. vasiliyzibrov (FID 830668) — 136 casts (Likes: 136, Recasts: 0, Replies: 0)
3. noicebot (FID 1057944) — 97 casts (Likes: 0, Recasts: 0, Replies: 119)
4. pugson (FID 557) — 88 casts (Likes: 84, Recasts: 7, Replies: 22)
5. ozgurper (FID 877655) — 85 casts (Likes: 85, Recasts: 12, Replies: 5)
6. brixbounty (FID 18723) — 84 casts (Likes: 83, Recasts: 2, Replies: 11)
7. verge (FID 432754) — 82 casts (Likes: 82, Recasts: 0, Replies: 0)
8. jachian (FID 5494) — 80 casts (Likes: 80, Recasts: 3, Replies: 24)
9. nounishprof (FID 4167) — 80 casts (Likes: 78, Recasts: 5, Replies: 14)
10. yth (FID 326487) — 71 casts (Likes: 71, Recasts: 0, Replies: 1)
11. dylsteck.eth (FID 616) — 68 casts (Likes: 68, Recasts: 10, Replies: 8)
12. juliettemeon.eth (FID 685132) — 65 casts (Likes: 65, Recasts: 5, Replies: 2)
13. huy199506 (FID 374099) — 62 casts (Likes: 59, Recasts: 10, Replies: 13)
14. zinger (FID 1407) — 62 casts (Likes: 60, Recasts: 11, Replies: 15)
15. koolkheart.eth (FID 310531) — 60 casts (Likes: 59, Recasts: 3, Replies: 28)
16. samantha (FID 1606) — 60 casts (Likes: 59, Recasts: 4, Replies: 14)
17. ashmoney.eth (FID 12938) — 59 casts (Likes: 59, Recasts: 9, Replies: 5)
18. jagdeesh (FID 17491) — 59 casts (Likes: 59, Recasts: 1, Replies: 0)
19. ciberdelia (FID 422910) — 58 casts (Likes: 55, Recasts: 12, Replies: 49)
20. qt (FID 18570) — 56 casts (Likes: 56, Recasts: 0, Replies: 11)
21. akash2539 (FID 645888) — 55 casts (Likes: 55, Recasts: 4, Replies: 0)
22. robin (FID 369) — 55 casts (Likes: 55, Recasts: 19, Replies: 7)
23. mikadoe.eth (FID 477126) — 54 casts (Likes: 54, Recasts: 12, Replies: 7)
24. linda (FID 12) — 54 casts (Likes: 52, Recasts: 23, Replies: 16)
25. bertwurst.eth (FID 864405) — 51 casts (Likes: 49, Recasts: 10, Replies: 16)

So I've asked ChatGPT to analyse the data from the Rewards Leaderboard Top 10 I shared yesterday (thanks for the tip @dosir). This is what it came up with

Should we do this again next week?

📊 Key Insights
- High concentration of influence and interaction among top leaderboard creators and their superfans — with some appearing as top fans for 5+ creators.

- A potentially self-reinforcing system — those at the top engage with one another and remain highly visible.

- New reward logic could reduce “circular value exchange” — ideally diversifying who earns and who gets seen.

- Some users (like monadver, ejire5, gfam) may be acting like “engagement miners”, systematically liking/commenting on top creators.

✅ Suggestions (If You're Evaluating the System)
- Introduce diminishing returns on repeated engagement from the same user to the same creator.

- Reward diversity of fans — e.g. reward creators who attract engagement from new or varied FIDs.

- Visibility of top fans could itself become a reward metric, encouraging healthy discovery vs mutual reinforcement.

[artist and dev] <>building things. chilling in tub often. doing things I like</>

$hamster /hamster 
martinvr.eth 
deploy.degen.eth

Yes let’s do that again next week. Nice one. Ai data analysis is always fun 👏

Head of Ecosystem @hyperplay / you would probably catch me reading, cooking or sipping on a good cup of café ☕️

Korean-Latina

That’s exactly what I am trying to say tho!

Just do it, you shouldn't have to think about who you interact with or not

Regarding the point of introducing “diminishing returns” > what if the person I am interacting with is really an internet friend you want interact with?

DAOnarcho-cybersyndicalist ☠︎hyperpunk ☭ /𝖘𝖈𝖚𝖒☠︎

😲ohhh! 

Ye I can’t do all that😅🥲

I've fetched them from snapchain directly, combined it with some other json sets I have

Yo where are you searching for all this data? Dune? Neynar? 

Like what if I wanted to see my lifetime tips where should I go?

I love it! Nice to have data behind the theories!

The Farcaster algo almost only shows you people you recently interacted with, this likely plays a big role in the engagement dynamics and rewards.

imo you should compare the amount of likes people get from people in their “inner circle” vs likes they get from others, at stack overflow one metric we used for voting rings was “these people are only ever liking each others content, not anyone else’s”

HuntTown

@mvr, you just received 415 applause from @cryptonjal for being a based builder 👏

🏆 Today's Current Rank: 119th
👏 Claps to Next Rank: 185

The Hunt Town Grant is a daily competition that rewards the top three builders with $HUNT backed NFT grants. Learn more at /hunt.

Allowance will be reset in 19:46:17 ⌛️

Interests: crypto, economics, TA & blockchain related innovations | 🔗 https://linktr.ee/cryptonjal 🔗 https://dune.com/nhejyht

I love that you are analysing this data so closely. It was inevitable that people would game the rewards system and I had my reservations when the rewards were increased. 
Great if we can stay one step ahead of the gamers and continue to reward more people that create genuine content and natural connections.

Great idea! Interesting to see behind the curtain how the current leaders are getting there. Love AI recommendations too. Chatgpt is great with these large data sets.

I think this is cool and we should do it this week again

@mvr, you just received 15,950 applause from @chancey-project for being a based builder 👏

🏆 Today's Current Rank: 6th
👏 Claps to Next Rank: 3,615

The Hunt Town Grant is a daily competition that rewards the top three builders with $HUNT backed NFT grants. Learn more at /hunt.

Allowance will be reset in 08:56:57 ⌛️

Hey, I'm building here! I'm building a lottery where the players call the shots!

https://www.getchancey.com/

Come hang out with me over at /chancey