<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/tags/machine-learning/best-of/2025/06" -->

---
title: Best Machine Learning posts — June 2025 | daily.dev
description: The most upvoted Machine Learning posts from June 2025, curated by the daily.dev community.
canonical: https://daily.dev/tags/machine-learning/best-of/2025/06
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:url: https://daily.dev/tags/machine-learning/best-of/2025/06
og:type: website
og:site_name: daily.dev
og:title: Best Machine Learning posts — June 2025 | daily.dev
og:description: The most upvoted Machine Learning posts from June 2025, curated by the daily.dev community.
og:image: https://media.daily.dev/image/upload/s--VAY5ToZt--/f_auto/v1724209435/public/daily.dev%20-%20open%20graph
---

# Best of Machine Learning — June 2025

1. 1  
[](/posts/coding-llms-from-the-ground-up-a-complete-course-zl0o8ruca "Coding LLMs from the Ground Up: A Complete Course")  
[![sebastianraschka's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/eb22d2e73d074c5598d31588ad16a51c)](/tags/[tag]/best-of/[year]/[month])  
5m read time • Jun 10, 2025  
### Coding LLMs from the Ground Up: A Complete Course  
Sebastian Raschka shares a comprehensive video course series on building Large Language Models from scratch using Python and PyTorch. The course covers seven key areas: environment setup, text data preprocessing and tokenization, attention mechanisms implementation, LLM architecture coding, pretraining on unlabeled data, classification fine-tuning, and instruction fine-tuning. The content serves as supplementary material to his book 'Build a Large Language Model (From Scratch)' and emphasizes hands-on learning through implementation rather than using pre-built frameworks.

+4  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/29cecca5f5bc16842bae6b2e96fb3f35?_a=AQAEulh)  
419  
5
2. 2  
[](/posts/ep167-top-20-ai-concepts-you-should-know-selocxsgb "EP167: Top 20 AI Concepts You Should Know")  
[![bytebytego's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/35be29234ee14d01a9cd049c52e12753)](/tags/[tag]/best-of/[year]/[month])  
7m read time • Jun 14, 2025  
### EP167: Top 20 AI Concepts You Should Know  
A comprehensive overview of 20 essential AI concepts including machine learning, deep learning, neural networks, NLP, computer vision, and transformers. Also covers the AI application stack for building RAG applications, featuring components like large language models, frameworks, vector databases, data extraction tools, and text embeddings. Additionally includes insights into Shopify's tech stack architecture and job opportunities in AI and software engineering.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/aeaf87694acd2a25c3a45aedc26b8926?_a=AQAEulh)  
204  
1
3. 3  
[](/posts/breaking-into-ai-engineering-in-2025--93xjryfpi "Breaking into AI Engineering in 2025.")  
[![swirlai's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/25542e29104c4f78b56442780718f69a)](/tags/[tag]/best-of/[year]/[month])  
10m read time • Jun 04, 2025  
### Breaking into AI Engineering in 2025.  
A comprehensive roadmap for becoming an AI Engineer in 2025, covering essential skills from Python fundamentals and LLM APIs to advanced topics like AI agents, RAG systems, and observability. The guide emphasizes learning fundamentals while building practical skills, starting with basic LLM integration and progressing through vector databases, prompt engineering, agentic systems, infrastructure deployment, and security considerations. Key recommendations include mastering FastAPI and Pydantic, understanding different LLM types and structured outputs, implementing RAG with proper data preprocessing, and learning agent design patterns like ReAct and task decomposition.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/5dd90914ce781c9785180d7caef208a4?_a=AQAEulh)  
203  
2
4. 4  
[](/posts/how-to-design-my-first-ai-agent-zdffwykif "How to Design My First AI Agent")  
[![tds's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tds)](/tags/[tag]/best-of/[year]/[month])  
10m read time • Jun 03, 2025  
### How to Design My First AI Agent  
A comprehensive guide to designing AI agents covering model selection, tooling choices, and reliability strategies. Explores different LLM options including OpenAI GPT-4, DeepSeek, Claude, and Mistral, each suited for specific use cases. Discusses infrastructure considerations, frameworks like LangGraph and Pydantic-AI, and security aspects. Emphasizes the importance of structured prompting techniques like Chain-of-Thought and ReAct, output validation, and failure handling to build reliable production-ready agents.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/1858f577f5761b7b29c35ff8ca74ee36?_a=AQAEulh)  
188
5. 5  
[](/posts/stop-taking-random-ai-courses---read-these-books-instead-jbxywdejx "STOP Taking Random AI Courses - Read These Books Instead")  
Video  
[![youtube's profile](https://media.daily.dev/image/upload/s--W5zMumpP--/f_auto/v1725350181/logos/youtube)](/tags/[tag]/best-of/[year]/[month])  
18m watch time • Jun 21, 2025  
### STOP Taking Random AI Courses - Read These Books Instead  
A comprehensive guide to learning AI and machine learning through structured resources rather than random courses. Covers five key areas: programming fundamentals with Python, mathematics and statistics foundations, traditional machine learning concepts, deep learning and LLMs, and AI engineering for production deployment. Emphasizes practical application over theoretical study, recommending specific books like 'Hands-On ML with Scikit-Learn and TensorFlow' and courses like Andrew Ng's specializations. Highlights the importance of understanding both foundational concepts and modern deployment practices for current AI engineering roles.

+5  
![Post Cover image](https://i.ytimg.com/vi/eE6yvtKLwvk/sddefault.jpg)  
164  
4
6. 6  
[](/posts/comic-ai-chronicles-state-of-the-art-output-1asd0pxya "(comic) AI Chronicles: State-of-the-art Output")  
[![workchronicles's profile](https://media.daily.dev/image/upload/s--V5O-tAlc--/f_auto/v1714799471/logos/workchronicles)](/tags/[tag]/best-of/[year]/[month])  
1m read time • Jun 17, 2025  
### (comic) AI Chronicles: State-of-the-art Output  
A humorous comic strip that satirizes the gap between AI marketing claims of 'state-of-the-art' performance and the actual quality of AI-generated outputs that developers encounter in practice.

+2  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/ce3575c84f08404c4dc0f070c13d1948?_a=AQAEulh)  
154  
8
7. 7  
[](/posts/48-most-popular-open-ml-datasets-knxhdfgmi "48 Most Popular Open ML Datasets")  
[![dailydoseofds's profile](https://media.daily.dev/image/upload/s--4IHQgTOw--/f_auto/v1710503712/logos/dailydoseofds)](/tags/[tag]/best-of/[year]/[month])  
4m read time • Jun 02, 2025  
### 48 Most Popular Open ML Datasets  
A comprehensive compilation of 48 widely-used open machine learning datasets organized by domain including computer vision (ImageNet, COCO), natural language processing (SQuAD, GLUE), recommendation systems (MovieLens, new Yambda-5B), tabular data (UCI datasets, Titanic), reinforcement learning (OpenAI Gym), and multimodal learning (LAION-5B, VQA). Each dataset is briefly described with its primary use case and key characteristics, serving as a reference guide for researchers and practitioners selecting appropriate datasets for their ML projects.

+4  
![Post Cover image](https://media.daily.dev/image/fetch/s--UfhrYjDp--/f_auto,pg_1,q_auto/https://substackcdn.com/image/fetch/w_1200%2Ch_600%2Cc_fill%2Cf_jpg%2Cq_auto:good%2Cfl_progressive:steep%2Cg_auto/https%253A%252F%252Fsubstack-post-media.s3.amazonaws.com%252Fpublic%252Fimages%252Fb6252207-10fc-4be3-aa5a-7f95bc4754ab_1246x1054.gif?_a=BAMAMiZY0)  
140  
1
8. 8  
[](/posts/the-10-most-important-lessons-20-years-of-mathematics-taught-me-2smbja0nb "The 10 Most Important Lessons 20 Years of Mathematics Taught Me")  
[![palindrome's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/cfdfeb66e965438eb7a539c98ba83494)](/tags/[tag]/best-of/[year]/[month])  
8m read time • Jun 25, 2025  
### The 10 Most Important Lessons 20 Years of Mathematics Taught Me  
A mathematician with 20 years of experience shares ten key lessons about learning and mastery. The core insights include the importance of understanding fundamentals before breaking rules, learning through hands-on problem solving rather than passive consumption, and recognizing that there are no shortcuts to expertise. The author emphasizes taking things slow to build deep understanding, tackling complexity one step at a time, and finding the right perspective to solve problems. Other key points include the power of asking questions without shame, the primacy of hard work over talent, and the importance of forging your own path rather than blindly following others' advice.

+3  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/b3f3b55475faa5cb2e583ad5351374da?_a=AQAEulh)  
132  
3
9. 9  
[](/posts/what-is-mcp-model-context-protocol--s16b1iajt "What is MCP (Model Context Protocol)?")  
[![Vijay Deepak's profile](https://media.daily.dev/image/upload/s--UmlolALr--/f_auto/v1729515300/avatars/avatar_9WH1spArmTebVCGG5Ww6b)](https://daily.dev/vijay%5Fdeepak)  
[![tarzzotech's profile](https://media.daily.dev/image/upload/s--JbxhDhp5--/f_auto,q_auto/v1693976635/squads/05e0f78f-c950-40c2-8913-bb3a1876a878)](/tags/[tag]/best-of/[year]/[month])  
Vijay Deepak  
@tarzzotech • Jun 04, 2025  
### What is MCP (Model Context Protocol)?

+3  
![Post Cover image](https://media.daily.dev/image/upload/s--1Jas5jyX--/f_auto/v1749047790/posts/s16b1IAJT?_a=BAMClqUq0)  
122  
2
10. 10  
[](/posts/ep169-rag-vs-agentic-rag-wiw6lb8hy "EP169: RAG vs Agentic RAG")  
[![bytebytego's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/35be29234ee14d01a9cd049c52e12753)](/tags/[tag]/best-of/[year]/[month])  
7m read time • Jun 28, 2025  
### EP169: RAG vs Agentic RAG  
RAG (Retrieval Augmented Generation) combines information retrieval with large language models, but traditional RAG has limitations in adaptability and real-time processing. Agentic RAG introduces AI agents that make decisions, select tools, and refine queries for more accurate responses. The comparison covers Kubernetes fundamentals including control planes, nodes, and key resources like Pods and Deployments. Six space-efficient data structures are highlighted: Bloom Filter, HyperLogLog, Cuckoo Filter, Minhash, SkipList, and Count-Min Sketch. Database normalization forms from 1NF to 4NF are explained for eliminating redundancy and enforcing data integrity.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/bc21c50573807f9cb2a71bb8707faa96?_a=AQAEulh)  
121  
1
11. 11  
[](/posts/implementing-vector-search-from-scratch-a-step-by-step-tutorial-c4rk9mfup "Implementing Vector Search from Scratch: A Step-by-Step Tutorial")  
[![mlm's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/795781ffb32446c39eba040feb64f505)](/tags/[tag]/best-of/[year]/[month])  
6m read time • Jun 10, 2025  
### Implementing Vector Search from Scratch: A Step-by-Step Tutorial  
A comprehensive tutorial demonstrating how to build a vector search engine from scratch using Python. Covers the three core steps of vector search: converting text to numerical vectors, calculating similarity using cosine similarity, and retrieving the most relevant results. Includes practical code examples with NumPy and Matplotlib, visualization of vector spaces, and explains the connection to RAG systems. The implementation uses simplified word embeddings and averaging techniques to make concepts accessible while maintaining the fundamental principles of semantic search.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/3a18e6f3d430cfe876352d7eb4d3017e?_a=AQAEulh)  
118
12. 12  
[](/posts/99-of-developers-don-t-get-llms-qthsfrpjn "99% of Developers Don't Get LLMs")  
Video  
[![codinggopher's profile](https://media.daily.dev/image/upload/s--pv2IKQMG--/f_auto/v1736753456/logos/codinggopher)](/tags/[tag]/best-of/[year]/[month])  
11m watch time • Jun 21, 2025  
### 99% of Developers Don't Get LLMs  
Large language models work by predicting the next token in a sequence using transformer architecture with self-attention mechanisms. They're trained on massive text datasets to learn patterns, grammar, and relationships between concepts. The transformer processes all tokens simultaneously rather than sequentially, allowing better capture of long-range dependencies. Generation happens through probability distributions over vocabulary, with techniques like temperature and top-k sampling controlling randomness. Models become more capable with scale, exhibiting emergent behaviors not present in smaller versions. Raw models are aligned with human preferences through reinforcement learning with human feedback (RLHF). Despite their fluency, LLMs have significant limitations including hallucination, lack of persistent memory, and sensitivity to input phrasing.

+4  
![Post Cover image](https://i.ytimg.com/vi/Kq8Iz9tTcSo/sddefault.jpg)  
104  
10
13. 13  
[](/posts/10-mcp-rag-and-ai-agents-projects-4tm9nanlx "10 MCP, RAG and AI Agents Projects")  
[![dailydoseofds's profile](https://media.daily.dev/image/upload/s--4IHQgTOw--/f_auto/v1710503712/logos/dailydoseofds)](/tags/[tag]/best-of/[year]/[month])  
3m read time • Jun 20, 2025  
### 10 MCP, RAG and AI Agents Projects  
A curated collection of 10 advanced AI engineering projects covering MCP-powered applications, RAG systems, and AI agents. Projects include video RAG with exact timestamp retrieval, corrective RAG with self-assessment, multi-agent flight booking systems, voice-enabled RAG agents, and local alternatives to ChatGPT's research features. The repository contains 70+ hands-on tutorials focusing on real-world implementations of LLMs, memory-enabled agents, multimodal document processing, and performance optimization techniques like binary quantization for 40x faster RAG systems.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/dc97fa89c864002c6ca1ef490264c20a?_a=AQAEulh)  
99
14. 14  
[](/posts/10-python-one-liners-that-will-simplify-feature-engineering-ehai4styi "10 Python One-Liners That Will Simplify Feature Engineering")  
[![mlm's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/795781ffb32446c39eba040feb64f505)](/tags/[tag]/best-of/[year]/[month])  
7m read time • Jun 03, 2025  
### 10 Python One-Liners That Will Simplify Feature Engineering  
Ten practical Python one-liners for feature engineering tasks including standardization, min-max scaling, polynomial features, one-hot encoding, discretization, logarithmic transformation, ratio creation, low variance removal, multiplicative interactions, and outlier tracking. Each technique uses popular libraries like scikit-learn and pandas to transform raw data into meaningful features for machine learning models.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/d1e9509bc1876db2ecda97696f106eee?_a=AQAEulh)  
82
15. 15  
[](/posts/best-5-open-source-llms-for-developers-chatgpt-alternatives-in-2025-nrciet1tq "Best 5 Open-Source LLMs for Developers: ChatGPT Alternatives in 2025")  
[![Suresh Mohan's profile](https://lh3.googleusercontent.com/a-/AOh14GiORQm3okwNI9Z01tYDa4YELb6j3F-hP-fbPVbSves=s100)](https://daily.dev/sureshmohan)  
[![syncfusion's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/064efc4834bd43b987bcda02e8ad6709)](/tags/[tag]/best-of/[year]/[month])  
9m read time • Jun 17, 2025  
### Best 5 Open-Source LLMs for Developers: ChatGPT Alternatives in 2025  
Five powerful open-source large language models offer cost-effective alternatives to ChatGPT for developers in 2025\. Llama 3 delivers GPT-3.5-level performance with commercial licensing freedom, while Mistral AI provides exceptional efficiency with smaller parameter counts. Falcon offers flexible model sizes from 7B to 180B parameters, BLOOM supports 46 natural languages for global applications, and Pythia serves as a research-grade suite for AI interpretability studies. These models enable local deployment, complete customization, and freedom from API restrictions, though they require careful consideration of hardware requirements and deployment strategies.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/31edb7e13a9f1020c03a13c2f1dcf1a0?_a=AQAEulh)  
70
16. 16  
[](/posts/10-mlops-tools-for-machine-learning-practitioners-to-know-ukt4svtct "10 MLOps Tools for Machine Learning Practitioners to Know")  
[![mlm's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/795781ffb32446c39eba040feb64f505)](/tags/[tag]/best-of/[year]/[month])  
4m read time • Jun 05, 2025  
### 10 MLOps Tools for Machine Learning Practitioners to Know  
MLOps combines machine learning with DevOps practices to streamline model lifecycle management from training to deployment. Ten essential tools are highlighted: MLflow for experiment tracking, Weights & Biases for visualization, Comet for monitoring, Airflow for workflow automation, Kubeflow for Kubernetes-based pipelines, DVC for data versioning, Metaflow for Python workflows, Pachyderm for data pipelines, Evidently AI for model monitoring, and TensorFlow Extended for complete ML pipelines. These tools address different aspects of MLOps including experiment tracking, workflow automation, data versioning, and model monitoring to help teams build reliable, production-ready machine learning systems.

+4  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/7df407994989a1052ca76e9359044077?_a=AQAEulh)  
68
17. 17  
[](/posts/chatgpt-polluted-the-world-forever-like-the-first-atom-bomb-zvis6spep "ChatGPT polluted the world forever, like the first atom bomb")  
[![theregister's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/66aa2113fdad463992ffcbf0e8963fda)](/tags/[tag]/best-of/[year]/[month])  
9m read time • Jun 15, 2025  
### ChatGPT polluted the world forever, like the first atom bomb  
AI researchers warn that ChatGPT's launch in 2022 created a permanent contamination problem for machine learning training data, similar to how nuclear testing contaminated metals. The concern is that AI models trained on synthetic data from other AI models will suffer from 'model collapse,' becoming less reliable over time. This creates competitive advantages for companies with access to pre-2022 'clean' data and may lead to AI monopolies. Proposed solutions include mandatory AI content labeling, federated learning approaches, and government regulation to preserve access to uncontaminated datasets.

+4  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/762da9d6b22d25502da704bc55fc3dff?_a=AQAEulh)  
61  
5
18. 18  
[](/posts/fine-tuning-llms-is-a-huge-waste-of-time-xdurhahlu "Fine-Tuning LLMs is a Huge Waste of Time")  
[![hn's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn)](/tags/[tag]/best-of/[year]/[month])  
9m read time • Jun 12, 2025  
### Fine-Tuning LLMs is a Huge Waste of Time  
Fine-tuning advanced LLMs for knowledge injection is counterproductive because it overwrites existing valuable information stored in densely interconnected neurons. Instead of adding knowledge, fine-tuning risks destroying the carefully built ecosystem of an already trained model. Better alternatives include retrieval-augmented generation (RAG), adapter modules like LoRA, and contextual prompting, which inject new information without damaging the underlying model's knowledge base. These modular approaches preserve the integrity of pre-trained networks while achieving the desired knowledge enhancement goals.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/b2ccc8bbb4f5f5f96304fc8f1dd55ccc?_a=AQAEulh)  
56  
2
19. 19  
[](/posts/vllm-a-quick-start-gzi5czdbj "vLLM: A Quick Start")  
[![towardsdev's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/2c710db2750a4a70835862534cb7c9d4)](/tags/[tag]/best-of/[year]/[month])  
4m read time • Jun 09, 2025  
### vLLM: A Quick Start  
vLLM is an open-source library optimized for high-throughput serving of large language models in production. Its core innovation, PagedAttention, manages memory more efficiently by breaking the key-value cache into fixed-size pages instead of contiguous buffers, similar to virtual memory in operating systems. The tutorial covers installation on macOS M1, serving models via OpenAI-compatible API, using the native Python API, and integrating with LangChain for enhanced tooling capabilities.

+5  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/b4a224f8405d2aefa9800ad41fbe6219?_a=AQAEulh)  
52
20. 20  
[](/posts/i-was-tired-of-scam-calls-so-i-built-an-ai-that-messes-with-them--eafjfob0i "I was tired of scam calls, so I built an AI that messes with them 😘")  
[![Aadil Ghani's profile](https://lh3.googleusercontent.com/a-/AOh14GhkQDRGzqTobLxwRg0cOpqSUQECoWth9RzOT3Ehgg=s100)](https://daily.dev/aadilghani)  
[![ralphnex's profile](https://media.daily.dev/image/upload/s--MUf4bHKa--/f_auto/v1749332327/squads/da505fd8-4403-49a4-b30a-010ea42d7cb6?_a=BAMClqUq0)](/tags/[tag]/best-of/[year]/[month])  
Aadil Ghani  
@ralphnex • Jun 12, 2025  
### I was tired of scam calls, so I built an AI that messes with them 😘

+4  
![Post Cover image](https://media.daily.dev/image/upload/s--UQvAk2Or--/f_auto/v1749730777/posts/eAFJFOB0I?_a=BAMClqUq0)  
43  
12
21. 21  
[](/posts/25-free-tutorials-to-build-production-ready-ai-agents-fast--x2dnc774x "25 FREE Tutorials to Build Production-Ready AI Agents Fast!")  
[![Nir Diamant's profile](https://avatars.githubusercontent.com/u/28316913?v=4&s=64)](https://daily.dev/nirdiamantai)  
[![diamantai's profile](https://media.daily.dev/image/upload/s--hxmk0969--/f_auto/v1729025329/squads/1d002e3a-2177-48e1-b9f4-33f8a09565dd)](/tags/[tag]/best-of/[year]/[month])  
Nir Diamant  
@diamantai • Jun 17, 2025  
### 25 FREE Tutorials to Build Production-Ready AI Agents Fast!

+4  
![Post Cover image](https://media.daily.dev/image/upload/s--AOTr_ra7--/f_auto/v1750162746/posts/x2dnC774X?_a=BAMClqUq0)  
40  
1
22. 22  
[](/posts/deploy-any-ml-model-rag-or-agent-as-an-mcp-server-wsfjmx927 "Deploy any ML model, RAG or Agent as an MCP server")  
[![dailydoseofds's profile](https://media.daily.dev/image/upload/s--4IHQgTOw--/f_auto/v1710503712/logos/dailydoseofds)](/tags/[tag]/best-of/[year]/[month])  
4m read time • Jun 18, 2025  
### Deploy any ML model, RAG or Agent as an MCP server  
LitServe now supports MCP (Model Context Protocol) integration through a dedicated endpoint, allowing any ML model, RAG system, or AI agent to be deployed as an MCP server. This eliminates the need for custom integration code for each application. The implementation involves defining input schemas, setup methods, and inference logic in a simple Python class structure. The article also covers a 4-part MCP crash course and demonstrates deploying a Qwen 3 Agentic RAG system using CrewAI, Firecrawl, and LitServe.

+4  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/d8325ececc949ce05ea2c91a40004fea?_a=AQAEulh)  
36
23. 23  
[](/posts/why-meta-stole-millions-of-books-to-train-ai-w6pivzcxp "Why Meta stole millions of books to train AI")  
Video  
[![hitenshow's profile](https://media.daily.dev/image/upload/s--HkTMmDYN--/f_auto/v1732810180/logos/hitenshow)](/tags/[tag]/best-of/[year]/[month])  
4m watch time • Jun 16, 2025  
### Why Meta stole millions of books to train AI  
Meta downloaded 82 terabytes of pirated books from shadow libraries like LibGen to train their Llama AI model, despite legal concerns from engineers. After publishers refused licensing deals deemed too expensive and slow, Meta chose piracy over falling behind competitors like OpenAI and Google. The pirated data improved Llama's performance by 5%, leading to 800 more correct answers. Meta covered their tracks by masking IP addresses and removing copyright tags, while relying on a fair use legal defense strategy shared across the AI industry when facing inevitable lawsuits from authors and publishers.

+3  
![Post Cover image](https://i.ytimg.com/vi/X_whIuJo7MY/sddefault.jpg)  
36  
16
24. 24  
[](/posts/ep168-ai-vs-machine-learning-vs-deep-learning-vs-generative-ai-nj2fqsl9r "EP168: AI Vs Machine Learning Vs Deep Learning Vs Generative AI")  
[![bytebytego's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/35be29234ee14d01a9cd049c52e12753)](/tags/[tag]/best-of/[year]/[month])  
8m read time • Jun 21, 2025  
### EP168: AI Vs Machine Learning Vs Deep Learning Vs Generative AI  
Explains the hierarchical relationship between AI, machine learning, deep learning, and generative AI, with AI as the overarching field and each subsequent term representing more specialized subsets. Covers SQL query execution through database subsystems including transport, query processor, execution engine, and storage engine. Lists 20 key AI agent concepts from basic agents to multi-agent systems and swarm intelligence. Describes RabbitMQ's message broker architecture using exchanges, queues, and bindings for routing messages between producers and consumers.

+5  
![Post Cover image](https://media.daily.dev/image/fetch/s--lp6etftb--/f_auto,pg_1,q_auto/https://substackcdn.com/image/fetch/%24s_%21NdIC%21%2Cw_1200%2Ch_600%2Cc_fill%2Cf_jpg%2Cq_auto:good%2Cfl_progressive:steep%2Cg_auto/https%253A%252F%252Fsubstack-post-media.s3.amazonaws.com%252Fpublic%252Fimages%252F5da93cca-2041-4071-bf5e-da4396b17b61_1280x1532.gif?_a=BAMAMiZY0)  
34
25. 25  
[](/posts/understanding-and-coding-the-kv-cache-in-llms-from-scratch-uemfq2msy "Understanding and Coding the KV Cache in LLMs from Scratch")  
[![sebastianraschka's profile](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/eb22d2e73d074c5598d31588ad16a51c)](/tags/[tag]/best-of/[year]/[month])  
14m read time • Jun 17, 2025  
### Understanding and Coding the KV Cache in LLMs from Scratch  
KV cache is a critical optimization technique for LLM inference that stores previously computed key and value vectors to avoid redundant calculations during text generation. The technique provides significant speed improvements (up to 5x in examples) by caching intermediate attention computations and reusing them for subsequent tokens. Implementation involves modifying the attention mechanism to store and retrieve cached values, though it increases memory usage and code complexity. The article provides a complete from-scratch implementation with performance comparisons and optimization strategies for production use.

+3  
![Post Cover image](https://media.daily.dev/image/upload/t_mobile_feed/v1/posts/29cecca5f5bc16842bae6b2e96fb3f35?_a=AQAEulh)  
33

[See all Machine Learning archives](/tags/machine-learning/best-of)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@graph":[{"@type":"CollectionPage","@id":"https://daily.dev/tags/machine-learning/best-of/2025/06#page","url":"https://daily.dev/tags/machine-learning/best-of/2025/06","name":"Best Machine Learning Posts — June 2025","description":"The most upvoted Machine Learning posts from June 2025, curated by the daily.dev community.","isPartOf":{"@type":"WebSite","url":"https://daily.dev"}},{"@type":"ItemList","@id":"https://daily.dev/tags/machine-learning/best-of/2025/06#items","numberOfItems":25,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/posts/coding-llms-from-the-ground-up-a-complete-course-zl0o8ruca","name":"Coding LLMs from the Ground Up: A Complete Course"},{"@type":"ListItem","position":2,"url":"https://daily.dev/posts/ep167-top-20-ai-concepts-you-should-know-selocxsgb","name":"EP167: Top 20 AI Concepts You Should Know"},{"@type":"ListItem","position":3,"url":"https://daily.dev/posts/breaking-into-ai-engineering-in-2025--93xjryfpi","name":"Breaking into AI Engineering in 2025."},{"@type":"ListItem","position":4,"url":"https://daily.dev/posts/how-to-design-my-first-ai-agent-zdffwykif","name":"How to Design My First AI Agent"},{"@type":"ListItem","position":5,"url":"https://daily.dev/posts/stop-taking-random-ai-courses---read-these-books-instead-jbxywdejx","name":"STOP Taking Random AI Courses - Read These Books Instead"},{"@type":"ListItem","position":6,"url":"https://daily.dev/posts/comic-ai-chronicles-state-of-the-art-output-1asd0pxya","name":"(comic) AI Chronicles: State-of-the-art Output"},{"@type":"ListItem","position":7,"url":"https://daily.dev/posts/48-most-popular-open-ml-datasets-knxhdfgmi","name":"48 Most Popular Open ML Datasets"},{"@type":"ListItem","position":8,"url":"https://daily.dev/posts/the-10-most-important-lessons-20-years-of-mathematics-taught-me-2smbja0nb","name":"The 10 Most Important Lessons 20 Years of Mathematics Taught Me"},{"@type":"ListItem","position":9,"url":"https://daily.dev/posts/what-is-mcp-model-context-protocol--s16b1iajt","name":"What is MCP (Model Context Protocol)?"},{"@type":"ListItem","position":10,"url":"https://daily.dev/posts/ep169-rag-vs-agentic-rag-wiw6lb8hy","name":"EP169: RAG vs Agentic RAG"},{"@type":"ListItem","position":11,"url":"https://daily.dev/posts/implementing-vector-search-from-scratch-a-step-by-step-tutorial-c4rk9mfup","name":"Implementing Vector Search from Scratch: A Step-by-Step Tutorial"},{"@type":"ListItem","position":12,"url":"https://daily.dev/posts/99-of-developers-don-t-get-llms-qthsfrpjn","name":"99% of Developers Don't Get LLMs"},{"@type":"ListItem","position":13,"url":"https://daily.dev/posts/10-mcp-rag-and-ai-agents-projects-4tm9nanlx","name":"10 MCP, RAG and AI Agents Projects"},{"@type":"ListItem","position":14,"url":"https://daily.dev/posts/10-python-one-liners-that-will-simplify-feature-engineering-ehai4styi","name":"10 Python One-Liners That Will Simplify Feature Engineering"},{"@type":"ListItem","position":15,"url":"https://daily.dev/posts/best-5-open-source-llms-for-developers-chatgpt-alternatives-in-2025-nrciet1tq","name":"Best 5 Open-Source LLMs for Developers: ChatGPT Alternatives in 2025"},{"@type":"ListItem","position":16,"url":"https://daily.dev/posts/10-mlops-tools-for-machine-learning-practitioners-to-know-ukt4svtct","name":"10 MLOps Tools for Machine Learning Practitioners to Know"},{"@type":"ListItem","position":17,"url":"https://daily.dev/posts/chatgpt-polluted-the-world-forever-like-the-first-atom-bomb-zvis6spep","name":"ChatGPT polluted the world forever, like the first atom bomb"},{"@type":"ListItem","position":18,"url":"https://daily.dev/posts/fine-tuning-llms-is-a-huge-waste-of-time-xdurhahlu","name":"Fine-Tuning LLMs is a Huge Waste of Time"},{"@type":"ListItem","position":19,"url":"https://daily.dev/posts/vllm-a-quick-start-gzi5czdbj","name":"vLLM: A Quick Start"},{"@type":"ListItem","position":20,"url":"https://daily.dev/posts/i-was-tired-of-scam-calls-so-i-built-an-ai-that-messes-with-them--eafjfob0i","name":"I was tired of scam calls, so I built an AI that messes with them 😘"},{"@type":"ListItem","position":21,"url":"https://daily.dev/posts/25-free-tutorials-to-build-production-ready-ai-agents-fast--x2dnc774x","name":"25 FREE Tutorials to Build Production-Ready AI Agents Fast!"},{"@type":"ListItem","position":22,"url":"https://daily.dev/posts/deploy-any-ml-model-rag-or-agent-as-an-mcp-server-wsfjmx927","name":"Deploy any ML model, RAG or Agent as an MCP server"},{"@type":"ListItem","position":23,"url":"https://daily.dev/posts/why-meta-stole-millions-of-books-to-train-ai-w6pivzcxp","name":"Why Meta stole millions of books to train AI"},{"@type":"ListItem","position":24,"url":"https://daily.dev/posts/ep168-ai-vs-machine-learning-vs-deep-learning-vs-generative-ai-nj2fqsl9r","name":"EP168: AI Vs Machine Learning Vs Deep Learning Vs Generative AI"},{"@type":"ListItem","position":25,"url":"https://daily.dev/posts/understanding-and-coding-the-kv-cache-in-llms-from-scratch-uemfq2msy","name":"Understanding and Coding the KV Cache in LLMs from Scratch"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Tags","item":"https://daily.dev/tags"},{"@type":"ListItem","position":3,"name":"Machine Learning","item":"https://daily.dev/tags/machine-learning"},{"@type":"ListItem","position":4,"name":"Best of","item":"https://daily.dev/tags/machine-learning/best-of"},{"@type":"ListItem","position":5,"name":"June 2025"}]}]}
```

