Good Reads

An LLM does not need to understand MCP

Story Link: https://hackteam.io/blog/your-llm-does-not-care-about-mcp/

Here's how I access all my Docker apps remotely

Story Link: https://www.xda-developers.com/heres-how-i-access-all-my-docker-apps-remotely/

21 Chunking Strategies for RAG

Story Link: https://ai.gopubby.com/21-chunking-strategies-for-rag-f28e4382d399

MoE vs Dense vs Hybrid LLM Architectures

Story Link: https://medium.com/@zaiinn440/moe-vs-dense-vs-hybrid-llm-architectures-9db18428dbe2 

RAG is dead, long live agentic retrieval

Story Link: https://www.llamaindex.ai/blog/rag-is-dead-long-live-agentic-retrieval

5 Error Handling Patterns in Python (Beyond Try-Except)

Story Link: https://www.kdnuggets.com/5-error-handling-patterns-in-python-beyond-try-except

An AWS technician gives us a tour of a data center in eastern Oregon

Story Link: https://www.aboutamazon.com/news/aws/aws-data-center-inside

LLM-as-a-Judge: A Practical Guide

Story Link: https://towardsdatascience.com/llm-as-a-judge-a-practical-guide/

How Transformers Work: A Detailed Exploration of Transformer Architecture

Story Link: https://www.datacamp.com/tutorial/how-transformers-work

Diffusion models explained simply

Story Link: https://www.seangoedecke.com/diffusion-models-explained/

How does Netflix manage to show you a movie without interruptions?

Story Link: https://newsletter.techworld-with-milan.com/p/how-does-netflix-manage-to-show-you

How Amazon Transformed System Design: A Modern Tech Revolution

Story Link: https://levelup.gitconnected.com/how-amazon-transformed-system-design-a-modern-tech-revolution-8bf68a166c4d

Deploying Large Language Models with llama.cpp and k3s

Story Link: https://www.hackster.io/shahizat/deploying-large-language-models-with-llama-cpp-and-k3s-24a237

Automate 90% of Your Work with AI Agents (Real Examples & Code Inside) 🚀 🤖

Story Link: https://dev.to/copilotkit/automate-90-of-your-work-with-ai-agents-real-examples-code-inside-46ke

Every Caching Strategy Explained in 5 Minutes

Story Link: https://www.swequiz.com/blog/every-caching-strategy-explained-in-5-minutes

CACM: Meta’s Hyperscale Infrastructure: Overview and Insights

Story Link: https://cacm.acm.org/research/metas-hyperscale-infrastructure-overview-and-insights/

Attention Is All You Need - Vanilla Transformer

PDF Link: https://arxiv.org/abs/1706.03762

What is Federated Learning?

Story Link: https://medium.com/pytorch/what-is-federated-learning-eaf329b98345

What Is Backward Integration?

Story Link: https://www.investopedia.com/terms/b/backwardintegration.asp