Sam Liebeskind
@samliebeskind
product partnerships at New_Public; previously community & growth @ Geneva
Sam Liebeskind
Groupvibe | Make Friends & Meet New People
groupvibe.com
I’ve been thinking a lot about this idea of transitioning people from a “tasks to accomplish” mentality to a “having areas of responsibility” mentality.
Musubi - Moderation Supercharged
musubilabs.ai
Friction is inevitable in human relationships. It can be uncomfortable, even maddening. Yet friction can be meaningful—as a check on selfish behavior or inflated self-regard; as a spur to look more closely at other people; as a way to better understand the foibles and fears we all share.
The Age of Anti-Social Media Is Here
Levels of Autonomy for AI Agents
arxiv.org
5 levels of autonomy: operator, collaborator, consultant, approver, observer
The pattern is the same: the most sophisticated platforms are treating user behavior as sequences, not snapshots, recognizing that static embeddings miss the temporal dynamics and session context of how people actually use these products.
Mike Cohen • How the Substack feed is learning to understand your reading journey
The difference becomes clear in how the feed responds to your behavior. Let’s say you click on a note about climate policy. In the old two-tower system, this single interaction would contribute minimally to your overall profile, especially if climate wasn’t already one of your core subscription topics. The model’s simplistic averaging approach... See more
Mike Cohen • How the Substack feed is learning to understand your reading journey
The key difference is that sequential models maintain a dynamic representation of your current state. As you move through your feed, clicking on posts, subscribing to publications, engaging with notes, the model updates its understanding of where you are. It’s not just updating a long-term profile of your tastes. It’s tracking the momentum and... See more
Mike Cohen • How the Substack feed is learning to understand your reading journey
The two-tower era: efficient but static
The two-tower architecture has been the workhorse of modern recommendation systems, and for good reason: it’s elegant, scalable, and remarkably effective at learning patterns from massive amounts of data. Here’s how it worked for us once we deployed it in early 2024.
The system had two neural networks working... See more
The two-tower architecture has been the workhorse of modern recommendation systems, and for good reason: it’s elegant, scalable, and remarkably effective at learning patterns from massive amounts of data. Here’s how it worked for us once we deployed it in early 2024.
The system had two neural networks working... See more