Why Your AI Search Evaluation Is Probably Wrong (And How to Fix It)
A five-step framework for building rigorous, reproducible AI search benchmarks — before you make six-figure infrastructure decisions The p…
AI & Analytics
50 articles
Machine Learning at Scale: Managing More Than One Model in Production
From one model to managing a massive portfolio: What 10 years in the industry taught me The post Machine Learning at Scale: Managing More Th…
Write C Code Without Learning C: The Magic of PythoC
Compile native, standalone applications using the Python syntax you already know. The post Write C Code Without Learning C: The Magic of P…
LatentVLA: Latent Reasoning Models for Autonomous Driving
What if natural language is not the best abstraction for driving? The post LatentVLA: Latent Reasoning Models for Autonomous Driving appeare…
Understanding Context and Contextual Retrieval in RAG
Why traditional RAG loses context and how contextual retrieval improves search result accuracy.
The AI Bubble Has a Data Science Escape Hatch
Five classic data science skills are becoming scarce in tech. A 90-day plan to build them while AI dominates attention.
Sarvam Edge: A Beginner’s Guide to On-Device AI for India
Sarvam Edge brings on-device AI to India: works offline, speaks local languages, and protects privacy on the device.
What Makes Quantum Machine Learning “Quantum”?
What makes Quantum Machine Learning 'quantum'? An overview of the current state and potential applications.
We Tried The New GPT-5.4 And it is The Most Powerful ChatGPT Has Ever Been
GPT-5.4 tested: the most powerful ChatGPT model yet, with improvements in reasoning, coding, and everyday tasks.
The Data Team’s Survival Guide for the Next Era of Data
Six pillars for data teams to simplify their stack and prepare for AI agents as primary data consumers.
The Black Box Problem: Why AI-Generated Code Stops Being Maintainable
Why AI-generated code becomes unmaintainable without structure, and how structured generation solves this problem.
How to Create Production-Ready Code with Claude Code
Practical guide to writing production-grade code with Claude Code and other coding agents.
New Update Makes GPT-5.3 Instant More Useful For Everyday Tasks
GPT-5.3 Instant update makes the model more useful for daily tasks with smoother and more helpful conversations.
NotebookLM Gets a Game-changing Feature: Check Out Cinematic Video Overviews
Google's NotebookLM gets cinematic video overviews: a new way to visually summarize research notes.
AI in Multiple GPUs: ZeRO & FSDP
Explanation of Zero Redundancy Optimizer (ZeRO) and FSDP for multi-GPU AI training, including PyTorch implementation.
How Human Work Will Remain Valuable in an AI World
Why human work remains valuable in an AI world: an analysis of the unique contribution of people alongside artificial intelligence.
PhysicEdit: Teaching Image Editing Models to Respect Physics
PhysicEdit teaches image editing models to respect the laws of physics during physical interactions in images.
5 Ways to Implement Variable Discretization
Five methods for variable discretization: converting continuous variables to discrete values for better modeling.
Stop Tuning Hyperparameters. Start Tuning Your Problem.
Why 80% of ML projects fail due to poor problem definition. A 5-step protocol to define the right problem.
Time Series Cross-Validation: A Guide to Techniques & Practical Implementation
Guide to time series cross-validation: techniques that preserve temporal integrity for reliable predictions.
Escaping the Prototype Mirage: Why Enterprise AI Stalls
Why enterprise AI projects get stuck in the prototype stage and how to move from prototype to production.
RAG with Hybrid Search: How Does Keyword Search Work?
Explanation of keyword search, TF-IDF, and BM25 in the context of RAG with hybrid search methods for better AI retrieval.
Graph Coloring You Can See
Visual explanation of graph coloring algorithms with Python, useful for optimization problems in data science.
Why You Should Stop Writing Loops in Pandas
Why you should avoid loops in Pandas: column-oriented thinking for faster and more professional data processing.
I Quit My $130,000 ML Engineer Job After Learning 4 Lessons
Four lessons from leaving an ML Engineer job: Insights on the realities behind dream tech jobs.
OpenClaw vs Claude Code: Which AI Coding Agent Should You Use in 2026?
Comparison of OpenClaw vs Claude Code in 2026: open-source flexibility versus Anthropic's ready-made AI coding agent.
Agentic RAG vs Classic RAG: From a Pipeline to a Control Loop
Comparing Agentic RAG and Classic RAG: when to choose adaptive retrieval loops versus simple pipelines.
20 OpenClaw Prompts to Automate Your Daily Life and Work
Twenty OpenClaw prompts to automate daily tasks and workflows with autonomous AI agents.
YOLOv3 Paper Walkthrough: Even Better, But Not That Much
Technical walkthrough of the YOLOv3 paper with a PyTorch implementation of the architecture from scratch.
The Machine Learning Lessons I’ve Learned This Month
Monthly ML lessons February 2026: knowledge sharing, documentation and MLOps as core topics for data professionals.
Code Less, Ship Faster: Building APIs with FastAPI
Guide to building APIs with FastAPI: path operations, Pydantic models, dependency injection, and automatic documentation.
10 Best YouTube Channels to Learn Generative AI
Ten best YouTube channels to learn Generative AI, selected for educational quality and practical usefulness.
Exciting Changes Are Coming to the TDS Author Payment Program
Towards Data Science is adjusting the author payment program with higher fees and more articles per month.
Building a RAG API with FastAPI
Tutorial: building a RAG API with FastAPI to make PDF reports searchable using generative AI.
Zero-Waste Agentic RAG: Designing Caching Architectures to Minimize Latency and LLM Costs at Scale
Caching architectures for Agentic RAG that reduce LLM costs by 30% through validation-aware, multi-tiered caching.
#492 – Rick Beato: Greatest Guitarists of All Time, History & Future of Music
Rick Beato shares his ranking of the greatest guitarists of all time and reflects on the history and future of music.
#491 – OpenClaw: The Viral AI Agent that Broke the Internet – Peter Steinberger
Peter Steinberger launched OpenClaw, a viral open-source AI agent that quickly became the fastest-growing project on GitHub.
#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI
Lex Fridman discusses the state of AI in 2026 in podcast #490: LLMs, scaling laws, AI agents, and the path to AGI.
#489 – Paul Rosolie: Uncontacted Tribes in the Amazon Jungle
Lex Fridman talks with naturalist Paul Rosolie about uncontacted tribes in the Amazon and wildlife conservation.
#488 – Infinity, Paradoxes that Broke Mathematics, Gödel Incompleteness & the Multiverse – Joel David Hamkins
Lex Fridman talks with a mathematician about infinity, paradoxes, and Gödel's incompleteness theorems.
#487 – Irving Finkel: Deciphering Secrets of Ancient Civilizations & Flood Myths
Lex Fridman talks with Irving Finkel about ancient civilizations, clay tablets, and deciphering ancient languages.
#486 – Michael Levin: Hidden Reality of Alien Intelligence & Biological Life
Biologist Michael Levin discusses with Lex Fridman how biological life possesses a hidden intelligence that challenges our understanding of …
#485 – David Kirtley: Nuclear Fusion, Plasma Physics, and the Future of Energy
Nuclear fusion engineer David Kirtley of Helion Energy discusses the future of fusion and the path to clean energy.
#484 – Dan Houser: GTA, Red Dead Redemption, Rockstar, Absurd & Future of Gaming
Dan Houser, co-founder of Rockstar Games, shares his vision on the creative future of gaming after GTA and Red Dead Redemption.
#483 – Julia Shaw: Criminal Psychology of Murder, Serial Killers, Memory & Sex
Criminal psychologist Julia Shaw discusses psychopathy, memory, and the dark side of human behavior.
#482 – Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature
Telegram founder Pavel Durov talks about freedom, censorship, power, and the future of private communication.
#481 – Norman Ohler: Hitler, Nazis, Drugs, WW2, Blitzkrieg, LSD, MKUltra & CIA
Historian Norman Ohler reveals the role of drugs in the Third Reich, from Hitler's personal use to the Blitzkrieg.
#480 – Dave Hone: T-Rex, Dinosaurs, Extinction, Evolution, and Jurassic Park
Paleontologist Dave Hone discusses T-Rex, dinosaurs, extinction, and the scientific accuracy of Jurassic Park.
#479 – Dave Plummer: Programming, Autism, and Old-School Microsoft Stories
Former Microsoft engineer Dave Plummer shares stories about Windows 95, Task Manager, and the programmer's life.
#478 – Scott Horton: The Case Against War and the Military Industrial Complex
Scott Horton argues against warfare and criticizes the military-industrial complex in the United States.