Hacker Newsnew | past | comments | ask | show | jobs | submit | semi_sentient's commentslogin

Follow-up posts for context (same series):

Part 2 – Data Layer (feature store to prevent online/offline skew; vector DB choices and pre- vs post-filtering): https://www.shaped.ai/blog/the-infrastructure-of-modern-rank...

Part 3 – MLOps Backbone (training pipelines, registry, GitOps deployment, monitoring/drift/A-B): https://www.shaped.ai/blog/the-infrastructure-of-modern-rank...

Happy to share more detail (autoscaling policies, index swaps, point-in-time joins, GPU batching) if helpful.


Modern ranking systems (feeds, search, recommendations) have strict latency budgets, often under 200 ms at p99. This write-up describes how we designed a production system using a decoupled microservice architecture for serving, a feature + vector store data layer, and an automated MLOps pipeline for training → deployment. This is less about modeling, more about the infrastructure that keeps it all running.


Retrieval is the stage where a ranking system narrows billions of items down to a few hundred candidates, fast enough for real-time use. It’s the least visible but most constrained layer: latency budgets, freshness, and recall all collide here.


A concise explainer of the standard four-stage architecture used in most modern recommendation and ranking systems: retrieval, scoring, ordering, and feedback.

It walks through how these stages connect in production systems like search, feeds, and content recommendations, with diagrams and examples.

Part of a five-part series exploring each stage in more detail this week.

Curious how others here are evolving these pipelines. Are you moving toward more unified (retrieval+scoring) models, or keeping stages separate for latency and control?


agreed, but looking at the article it looks like you can turn this personalization bit up or down though to find the mama bear/just right level?


Yeah exactly. I was really worried about reducing the serendipity that HN provides (as it's arguably why I've used it for so long as well) but the configurability allows it so that everyone can tweak their level of personalization to get their perfect goldilocks level.


What is the just right level when tuning in one's echo chamber?


shrug maybe the solution on something like this is where every nth post is a personalized one.


sneeze I do that by skimming things and clicking on every nth post that interests me


the "mama bear/just right level" I love this so much


I have a sinking sensation this phrase will pop up in a meeting now.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: