@mvr
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.
23 replies
6 recasts
33 reactions