Mohamed Arbi
@goodnight7.bsky.social
ML nerd | Qdrant star | Google DSC Lead '23 Portfolio: https://mohamedarbi.xyz/
Great @qdrant_engine Office Hours this week! Highlights: ⬩ Multitenant search in Qdrant ⬩ My Chrome extension for semantic AI bookmarking, hybrid (dense + sparse) search, AI summaries & bulk URL ingestion on your own cluster ⬩ Qdrant Skills ⬩ Benchmarking & retrieval quality
New addition to qdrant-resources Added Quantization Face-Off, benchmarking Qdrant's Scalar, Product, and Binary Quantization on memory, recall, and latency (TurboQuant soon) github.com/Goodnight...
If you’re tired of vector databases eating up all your RAM this is the deep-dive you need Covers why TurboQuant is mathematically outperforming standard BQ/SQ and how it effectively 'cheats physics' to keep recall high at extreme compression Check it out: mohamedarbi.xyz/post...
62k impressions in one LinkedIn post about MRL 🔥 Who said technical ML content doesn’t reach people?
A robot shouldn't need 5G to "think." I’ve documented how Qdrant Edge enables the shift to local-first AI, using quantization and in-process execution to run high-performance vector search on restricted hardware. Read more: mohamedarbi.xyz/post...
New tool for @qdrant.bsky.social monitoring: qdrant-exporter this Prometheus exporter tracks collection health, vector counts and status. the Go core is stable Python SDK still "work in progress" and needs some care soon Check it out github.com/Goodnight77/... docs: qdrant-exporter.vercel.app
2025 was a year of learning, building, and sacrificing a lot of sleep. I wrote a reflection on the lessons, mistakes, and small wins that shaped the year and how they are influencing how I think about 2026
2025: A Year of Growth and AI
Reflecting on my journey, hackathons, and community contributions.
mohamedarbinsibi.onrender.com
🎉 What a Git Year I had! I created 34 public repos, gained 144 stars and 17 forks and pushed 1176 public commits! ➡️ Follow me on GitHub: github.com/Goodnight77 Tried out @cle-does-things.bsky.social’s GitYear app and it nailed it Check it out if you want your own GitHub recap gityear.re
Goodnight77 - Overview
Goodnight77 has 51 repositories available. Follow their code on GitHub.
github.com
@qdrant_engine just launched Qdrant Academy, a free hands-on course that takes you from vector basics to building real-world search systems Learn embeddings, indexing hybrid search, and scaling all in one place Start here: qdrant.tech/course/e... Playlist lnkd.in/g2MkihPn?utm...
Production-Ready RAG System with Qdrant A new article by Rithvik K showcases how Qdrant powers multi-tenant vector storage in a production-grade RAG setup, integrating real-time PDF ingestion, streaming search, and LLM inference with LangGraph AI. Read the full article: t.co/jcaZ0KFS8c
Deploying a Production-Ready RAG on Kubernetes: Multi-Tenant Qdrant + Streaming PDF Ingestion + LLM…
Retrieval-Augmented Generation (RAG) has quickly become the pillar of modern enterprise AI systems everything from intelligent document…
medium.com
Me: Considering a startup Also me: Watching Sam Altman tell me everything you think about is wrong
Sam Altman - How to Succeed with a Startup
Sam Altman, President of Y Combinator, shares his thoughts on how you can succeed with a startup. Startup School is YC's free online program for founders. Sign up to access the full curriculum and over $100k in deals! https://www.startupschool.org/ Chapters (Powered by https://bit.ly/chapterme-yc)
youtube.com
guess im pivoting my job search from europe to China now XD
You ve been reading #research papers wrong the whole time, they were never novels watch the full wisdom in this insightful video by @AndrewYNg : www.youtube.com/watc... also check this summary: forums.fast.ai/t/how...
Stanford CS230: Deep Learning | Autumn 2018 | Lecture 8 - Career Advice / Reading Research Papers
Andrew Ng, Adjunct Professor & Kian Katanforoosh, Lecturer - Stanford University http://onlinehub.stanford.edu/ Andrew Ng Adjunct Professor, Computer Science Kian Katanforoosh Lecturer, Computer Science To follow along with the course schedule and syllabus, visit: http://cs230.stanford.edu/
youtube.com
Here is why AI won't replace jobs, good talk by Garry Tan @garrytan
What Everyone Is Getting Wrong About AI And Jobs
For years, we've heard two major narratives about AI. One predicting the end of human work, the other dismissing it as hype. The truth is more nuanced, and more hopeful. From radiology to software engineering, the pattern repeats: as technology makes tasks cheaper and faster, demand for human creat
youtube.com
🚀 Exciting news! We’ve just launched the Qdrant Academy 🎓 Dive into interactive courses and level up your vector search skills with Qdrant. Ready to learn, contribute, and grow with us? Link to the announcement: qdrant.tech/blog/qdrant-... #Qdrant #VectorSearch #DataScience #MachineLearning
Qdrant Academy Launches with Qdrant Essentials Course - Qdrant
The free, self-service, and online Qdrant Academy site has launched with its first comprehensive course, Qdrant Essentials. Read to learn more.
qdrant.tech
Yesterday, Meta announced Monarch, a new framework for distributed programming that scales big tasks like cluster management and model training while keeping high performance Pytorch blog: pytorch.org/blog/int...
Umar Jamil @hkproj once said : "Don't complain you slept only 4 hours today, be happy you have 20 hours to code CUDA kernels."
Me: bored Brain: installing creativity update… 3% completed
You Need to Be Bored. Here's Why.
Boredom isn’t a bug—it’s a feature. Harvard professor Arthur C. Brooks explains why boredom unlocks creativity, activates a powerful brain network, and might even protect you from depression. Learn how the mind wanders—and why that’s a very good thing. For more insights on leadership, success, and
youtube.com
I hate French, but I guess I'm going to enjoy listening to this talk anyway
Me: time to learn more GPU programming Monkey brain: Or… we could scroll memes instead 🐒
How to Trick Monkey Brain To Like Doing Hard Things (Dopamine Detox)
Monkey loves TikTok, games, and quick fun—but hates hard things. In this video, discover how dopamine tricks Monkey, why studying feels like torture, and how simple hacks—like a dopamine detox, smart rewards, and a few clever tricks—can make hard things feel easier (and even fun). 📍Note: Monkey kn
youtube.com
Me: busy. Also me: drops everything to watch this masterpiece on RL, quantization & Agents by @danielhanchen
[Full Workshop] Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han
Why is Reinforcement Learning (RL) suddenly everywhere, and is it truly effective? Have LLMs hit a plateau in terms of intelligence and capabilities, or is RL the breakthrough they need? In this workshop, we'll dive into the fundamentals of RL, what makes a good reward function, and how RL can help
youtube.com
Had a great time at the Qdrant Hangout Office Hours 💚 Brian O’Grady shared scaling tips, Joshua Mo walked through RIG framework (#in-rust-we-trust), @cle-does-things.bsky.social demoed #LlamaAgents, and Tarun R Jain talked #PyCon.
Here's the link to @qdrant.bsky.social Discord Office Hours today at 5pm CEST. Come chat, ask questions, or share your projects discord.com/events/9...
