[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@Vorsik2 Vorsik
Vorsik posts on X about decentralized, gpu, faster the most. They currently have XXX followers and X posts still getting attention that total XX engagements in the last XX hours.
Engagements: XX #
- X Months XX -XX%
- X Year XXXXX -XX%
Mentions: X #
- X Months X -XX%
- X Year XX -XX%
Followers: XXX #
- X Months XXX -XXXX%
- X Year XXX -XX%
CreatorRank: undefined #
Social Influence #
Social category influence cryptocurrencies XXXXX%
Social topic influence decentralized #4135, gpu 16.67%, faster XXXXX%
Top Social Posts #
Top posts by engagements in the last XX hours
"3. Post-training language models using reinforcement learning (RL) have become one of the most effective ways to enhance reasoning capabilities. But there's a problem: scaling RL is an expensive unreliable process often requiring carefully designed infrastructure"
X Link @Vorsik2 2025-10-21T18:48Z XXX followers, X engagements
"4. Warm sAmpling Policy Optimization (SAPO) is a fully decentralized and asynchronous post-training reinforcement learning algorithm. Instead of centralized GPU clusters SAPO is designed to work with large numbers of heterogeneous nodes"
X Link @Vorsik2 2025-10-21T18:48Z XXX followers, XX engagements
"5. SAPO demonstrates that sharing expertise can be a key benefit of post-training AI. It allows models to train faster communities to directly contribute to progress and reduces the cost and instability of scaling"
X Link @Vorsik2 2025-10-21T18:48Z XXX followers, X engagements
"6. 🙌With its collaborative reinforcement learning SAPO represents a new paradigm: decentralized communities of models (and people) can train each other. It's a scalable open and practical path to more powerful reasoning capabilities"
X Link @Vorsik2 2025-10-21T18:48Z XXX followers, X engagements