[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.] #  @rajammanabrolu Prithviraj (Raj) Ammanabrolu Prithviraj (Raj) Ammanabrolu posts on X about trust me, collab the most. They currently have XXXXX followers and X posts still getting attention that total XXXXX engagements in the last XX hours. ### Engagements: XXXXX [#](/creator/twitter::1115817574078582785/interactions)  - X Week XXXXX +4,631% - X Month XXXXX +153% - X Months XXXXXX -XX% - X Year XXXXXXX +20% ### Mentions: X [#](/creator/twitter::1115817574078582785/posts_active)  - X Week X no change - X Month X -XX% - X Months XX +11% - X Year XX -XXXX% ### Followers: XXXXX [#](/creator/twitter::1115817574078582785/followers)  - X Week XXXXX +0.51% - X Month XXXXX +1.60% - X Months XXXXX +10% - X Year XXXXX +47% ### CreatorRank: XXXXXXXXX [#](/creator/twitter::1115817574078582785/influencer_rank)  ### Social Influence [#](/creator/twitter::1115817574078582785/influence) --- **Social topic influence** [trust me](/topic/trust-me) 33.33%, [collab](/topic/collab) XXXXX% **Top accounts mentioned or mentioned by** [@ccui9](/creator/undefined) [@jennyshen056](/creator/undefined) ### Top Social Posts [#](/creator/twitter::1115817574078582785/posts) --- Top posts by engagements in the last XX hours "We've been quite motivated by the idea of trying to find scalable levers to balance between safety and capabilities. Process/fine grained rewards are a great way but it's hard to scale for non verifiable domains. Trust me I spent the last couple of years trying. So we figured out a way to train PRMs across domains with just outcome data + train multi objective policies with vectorized rewards on top My fav part is that one of the domains we tested on was real data collected from my classroom and at Georgia Tech for over a year with a tool that helps with AI oral assessment in class (think AI" [X Link](https://x.com/rajammanabrolu/status/1983253152926445600) [@rajammanabrolu](/creator/x/rajammanabrolu) 2025-10-28T19:22Z 7707 followers, 2010 engagements "courtesy @ccui9 and Georgia Tech collab with Ray Hung if you're an instructor thinking of using these in your own classes" [X Link](https://x.com/rajammanabrolu/status/1983253655227899987) [@rajammanabrolu](/creator/x/rajammanabrolu) 2025-10-28T19:24Z 7707 followers, XXX engagements
[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.]
@rajammanabrolu Prithviraj (Raj) Ammanabrolu
Prithviraj (Raj) Ammanabrolu posts on X about trust me, collab the most. They currently have XXXXX followers and X posts still getting attention that total XXXXX engagements in the last XX hours.
Engagements: XXXXX #
- X Week XXXXX +4,631%
- X Month XXXXX +153%
- X Months XXXXXX -XX%
- X Year XXXXXXX +20%
Mentions: X #
- X Week X no change
- X Month X -XX%
- X Months XX +11%
- X Year XX -XXXX%
Followers: XXXXX #
- X Week XXXXX +0.51%
- X Month XXXXX +1.60%
- X Months XXXXX +10%
- X Year XXXXX +47%
CreatorRank: XXXXXXXXX #
Social Influence #
Social topic influence trust me 33.33%, collab XXXXX%
Top accounts mentioned or mentioned by @ccui9 @jennyshen056
Top Social Posts #
Top posts by engagements in the last XX hours
"We've been quite motivated by the idea of trying to find scalable levers to balance between safety and capabilities. Process/fine grained rewards are a great way but it's hard to scale for non verifiable domains. Trust me I spent the last couple of years trying. So we figured out a way to train PRMs across domains with just outcome data + train multi objective policies with vectorized rewards on top My fav part is that one of the domains we tested on was real data collected from my classroom and at Georgia Tech for over a year with a tool that helps with AI oral assessment in class (think AI"
X Link @rajammanabrolu 2025-10-28T19:22Z 7707 followers, 2010 engagements
"courtesy @ccui9 and Georgia Tech collab with Ray Hung if you're an instructor thinking of using these in your own classes"
X Link @rajammanabrolu 2025-10-28T19:24Z 7707 followers, XXX engagements