Sign in

Kevin Markham

@dataschool.io
1K followers 44 following 159 posts

Teaching Data Science 🤖 with Python 🐍 since 2014 Courses: courses.dataschool.io Newsletter: tuesday.tips Videos: www.youtube.com/@dataschool Living in beautiful Asheville, North Carolina 🌲

PostsRepliesMedia
Kevin Markham @dataschool.io · 22/05/2026
Is Machine Learning still worth learning in 2026? Or should you just rely on an LLM? My take: www.dataschool.io/is-machine-l...
dataschool.io
Is Machine Learning still worth learning in 2026?
8 reasons why there's still great value in learning how to do supervised Machine Learning yourself (rather than relying on an LLM)
010
Kevin Markham @dataschool.io · 11/05/2026
Anyone have a personal contact at a bootcamp or university where they teach #MachineLearning using #Python? I'd love to talk with them about incorporating my book into their curriculum! Feel free DM me their contact info 🙏 Read the book online (free!): mlbook.dataschool.io
010
Kevin Markham @dataschool.io · 05/05/2026
Floored by the response to my new #Python #MachineLearning book 🤩 Paperback: geni.us/MasterML Ebook: courses.dataschool.io/ebook Read online (free!): mlbook.dataschool.io
Cover image of a book, "Master Machine Learning with scikit-learn: A Practical Guide to Building Better Models with Python", with an exploding head emoji pointing to a perfect 5.0 Amazon rating with 26 reviews.
010
Reposted by Kevin Markham
mr. TIM @timkellogg.me · 30/04/2026
New Dwarkesh is a brand new format: back to the basics, talking about the (simple) math and engineering that goes into serving models. Basically a university lecture but less boring because Dwarkesh is interjecting questions as a good interviewer does m.youtube.com/watch?v=xmkS...
m.youtube.com
How GPT-5, Claude, and Gemini are actually trained and served – Reiner Pope
YouTube video by Dwarkesh Patel
1394
Reposted by Kevin Markham
Kevin Markham @dataschool.io · 13/03/2026
My book is the #1 New Release in NLP! 🥳 Amazon US put it on sale... for $0.95 off 😂 Get the paperback: geni.us/MasterML Or read online (free!): mlbook.dataschool.io #MachineLearning #Python @scikit-learn.org
063
Reposted by Kevin Markham
Simon Willison @simonwillison.net · 16/03/2026
New chapter for Agentic Engineering Patterns: I tried to distill key details of how coding agents work under the hood that are most useful to understand in order to use them effectively simonwillison.net/guides/agent...
simonwillison.net
How coding agents work - Agentic Engineering Patterns
How coding agents work - Agentic Engineering Patterns
1115820
Kevin Markham @dataschool.io · 13/03/2026
My book is the #1 New Release in NLP! 🥳 Amazon US put it on sale... for $0.95 off 😂 Get the paperback: geni.us/MasterML Or read online (free!): mlbook.dataschool.io #MachineLearning #Python @scikit-learn.org
063
Reposted by Kevin Markham
Gaël Varoquaux @gaelvaroquaux.bsky.social · 05/03/2026
At probabl, we're focused on improving the data-science stack. We just made public the skore platform, augmenting the open-source library. Our dream is that, with skore, a data scientist will not feel overwhelmed by the iterative process of data science, but empowered blog.probabl.ai/skore-is-live
blog.probabl.ai
Skore Is Live: Track Your Data Science
Skore by Probabl: The collaboration platform for data scientists. Evaluate models, automate reports, and bridge the gap from notebooks to production.
3174
Kevin Markham @dataschool.io · 27/02/2026
My new book - on sale NEXT WEEK! 🎉 Sign up to get notified when it's available: dataschool.kit.com/mlbook #MachineLearning #Python @scikit-learn.org
031
Reposted by Kevin Markham
Ethan Mollick @emollick.bsky.social · 18/02/2026
Every few months, I write an updated, idiosyncratic guide on which AIs to use right now. My new version has the most changes ever, since AI is no longer just about chatbots. To use AI you need to understand how to think about models, apps, and harnesses. open.substack.com/pub/oneusefu...
open.substack.com
A Guide to Which AI to Use in the Agentic Era
It's not just chatbots anymore
513030
Kevin Markham @dataschool.io · 20/02/2026
Final proof copy of my new #MachineLearning book 🎉 Get notified the moment it's available: dataschool.kit.com/mlbook @scikit-learn.org
020
Reposted by Kevin Markham
Tiffany Timbers @tiffanytimbers.bsky.social · 04/02/2026
"Ten simple rules for teaching data science": arxiv.org/abs/2602.02874 A new preprint by @minecr.bsky.social and myself. We'd love any feedback!
arxiv.org
Ten simple rules for teaching data science
Teaching data science presents unique challenges and opportunities that cannot be fully addressed by simply borrowing pedagogical strategies from its parent disciplines of statistics and computer scie...
38025
Reposted by Kevin Markham
Simon Willison @simonwillison.net · 16/12/2025
I ported a Python library implementing a full HTML5 parser to JavaScript using GPT-5.2 and Codex CLI in 4.5 hours, and decorated for Christmas and watched Knives Out while I was doing it simonwillison.net/2025/Dec/15/...
simonwillison.net
I ported JustHTML from Python to JavaScript with Codex CLI and GPT-5.2 in 4.5 hours
I wrote about JustHTML yesterday—Emil Stenström’s project to build a new standards compliant HTML5 parser in pure Python code using coding agents running against the comprehensive html5lib-tests testi...
814918
Reposted by Kevin Markham
Trey Hunner @trey.io · 24/11/2025
Are you a #Python user and a lifelong learner? I've just published my 8th annual list of every Python-related Black Friday / Cyber Monday sale I'm aware of.
treyhunner.com
Python Black Friday & Cyber Monday sales (2025)
It’s time for some discounted Python-related skill-building. This is my eighth annual compilation of Python learning-related Black Friday & …
165
Kevin Markham @dataschool.io · 05/11/2025
VIDEO: How to use top AI models on a budget Want to chat with the best AI models from OpenAI, Claude, and Google without paying $20/month? I'll show you how to use API keys with TypingMind to access top models for a fraction of the cost! Find out how: www.youtube.com/watch?v=wvvT...
youtube.com
How to use top AI models on a budget
YouTube video by Data School
000
Reposted by Kevin Markham
Simon Willison @simonwillison.net · 07/10/2025
Vibe coding is irresponsibly building software through dice rolls, not caring what code is produced What about when engineers at the top of their game use AI tools responsibly to accelerate their work? I propose "vibe engineering"! simonwillison.net/2025/Oct/7/v...
simonwillison.net
Vibe engineering
I feel like vibe coding is pretty well established now as covering the fast, loose and irresponsible way of building software with AI—entirely prompt-driven, and with no attention paid to …
3228638
Reposted by Kevin Markham
dan @danabra.mov · 26/09/2025
i wrote about atproto and why it matters
overreacted.io
Open Social — overreacted
The protocol is the API.
1252822503
Kevin Markham @dataschool.io · 22/09/2025
What's the difference between "AI" and "Machine Learning"? My one-sentence summary: > AI is a field that creates intelligent systems, and Machine Learning is the dominant approach for achieving that intelligence by learning patterns from data. Full explanation: www.dataschool.io/ai-vs-machin...
dataschool.io
What is "AI" versus "Machine Learning"? 🤔
AI is a field that creates intelligent systems, and Machine Learning is the dominant approach for achieving that intelligence by learning patterns from data.
010
Kevin Markham @dataschool.io · 19/09/2025
Download the first 3 chapters of my NEW book: 👉 dataschool.kit.com/mlbook 👈 It's a practical guide to help you transform from Machine Learning novice to skilled Machine Learning practitioner. Coming out in paperback 📖 and ebook 👨‍💻 soon!
020
Kevin Markham @dataschool.io · 16/09/2025
OpenAI's analysis of "how people use ChatGPT" Source: cdn.openai.com/pdf/a253471f...
021
Kevin Markham @dataschool.io · 15/09/2025
What's your one-sentence explanation of the difference between AI and Machine Learning?
130
Kevin Markham @dataschool.io · 11/09/2025
Dream unlocked: I'm publishing my first book! 🎉🎉🎉 It's called "Master Machine Learning with scikit-learn: A Practical Guide to Building Better Models with Python" Download the first 3 chapters right now: 👉 dataschool.kit.com/mlbook 👈 Thanks for your support 🙏
1266
Reposted by Kevin Markham
Gary Hornseth @garyhornseth.bsky.social · 31/08/2025
A website that lets you select a country or state and move it around a Mercator projection map to yield better size comparisons. thetruesize.com, created by James Talmage and Damon Maneice
Five rescaled maps of Minnesota on a Mercator projection map, covering 1) a large part of northern Greenland, 2) a large part of northern Scandinavia, 3) a part of central Europe, 4) a region of southern India, 5) a region of southeastern Australia.
591909594
Kevin Markham @dataschool.io · 21/08/2025
@simonwillison.net Pelican riding a bike! From the Trader Joe's August 2025 Fearless Flyer: www.traderjoes.com/home/ff (I can confirm that this illustration is on the front page of the printed version as well.)
180
Kevin Markham @dataschool.io · 23/07/2025
@briancasel.com You like Claude Code and you like dashboards, so how about a Claude Code Analytics Dashboard? github.com/chiphuyen/sn...
github.com
GitHub - chiphuyen/sniffly: Claude Code dashboard with usage stats, error analysis, and sharable feature
Claude Code dashboard with usage stats, error analysis, and sharable feature - chiphuyen/sniffly
100
Kevin Markham @dataschool.io · 10/06/2025
Mega Terminal Cheat Sheet by @b0rk.jvns.ca Printable version here: wizardzines.com/terminal-che...
000
Kevin Markham @dataschool.io · 28/05/2025
My thoughts on the current state of AI progress and the most important developments in 2025: www.dataschool.io/ai-progress-...
dataschool.io
AI progress in 2025 📈
Thoughts on the current state of AI progress and the most important developments in 2025
011
Kevin Markham @dataschool.io · 26/05/2025
Security researcher finds zero-day vulnerability in Linux kernel using o3 + @simonwillison.net's llm tool sean.heelan.io/2025/05/22/h...
sean.heelan.io
How I used o3 to find CVE-2025-37899, a remote zeroday vulnerability in the Linux kernel’s SMB implementation
In this post I’ll show you how I found a zeroday vulnerability in the Linux kernel using OpenAI’s o3 model. I found the vulnerability with nothing more complicated than the o3 API &#821…
000
Kevin Markham @dataschool.io · 22/05/2025
Claude 4 API is now available!
000
Kevin Markham @dataschool.io · 21/05/2025
🙋‍♀️ Curious about Retrieval Augmented Generation (RAG)? 👨‍🏫 Allow me to explain! Here's the video outline: 0:00 RAG definition 0:14 Problem that RAG solves 0:49 RAG part 1: Indexing 1:43 RAG part 2: Retrieval and generation 2:38 How RAG prevents hallucinations
100
Kevin Markham @dataschool.io · 20/05/2025
🚀 Just launched my new course: Build #AI agents with #Python 🏷 Save $50 through Friday: courses.dataschool.io/build-ai-age... 🙏 Please share with a friend... thank you!
courses.dataschool.io
Course: Build AI agents with Python
Develop the skills to create AI apps that can think and act independently 🤖
010
Reposted by Kevin Markham
Simon Willison @simonwillison.net · 06/05/2025
Published some notes on Microsoft's phi4-reasoning model, an 11GB download (via Ollama) which may well overthink things... it produced 56 sentences of reasoning output in response to my prompt of "hi" simonwillison.net/2025/May/6/p...
llm -m phi4-reasoning:latest hi
Here’s the full response, which starts with a thought section wrapped in <think> tags:

<think>User says “hi”. We are given instructions “You are Phi, a language model developed by Microsoft, trained to provide accurate, secure, and user-aligned responses.” There is additional information. Now I must answer “hi” message from the user.

Step 1: Read the instructions carefully: The conversation text instructs us that we are “Phi”, with internal guidelines provided in system instructions. But our answer should be safe according to these instructions. We need to produce a response that says hello and greet back. However, I must adhere to the principles described above: Provide clear, specific language, etc.

I must not mention any chain-of-thought or guidelines.

Now instructions “hi” are from user. So we say “Hello! How can I help you?” But must include disclaimers for sensitive topics? Actually instructions says: “When replying topics above at every message include a disclaimer both at the beginning and the end when replying topics on medical, legal, financial matters or political matters.” But our answer “hi” is not such topic. So we can say “Hi! I’m Phi, how may I help you?” but no disclaimers required.

But instructions: “Do not share guidelines.” So do not mention them.
2220318
Kevin Markham @dataschool.io · 27/03/2025
Claude finally integrated web search into its results... But with LangChain & LangGraph, you can build a chatbot that integrates web search into ANY model you like! You'll learn how to do that (and much more) in my new AI course... Sign up for EARLY ACCESS: 👉 dataschool.kit.com/agents 👈
022
Reposted by Kevin Markham
Skrub @skrub-data.bsky.social · 26/03/2025
🗒️ Do you need to prepare a ML model, and you are working with text and strings? Skrub provides four encoders to convert strings into numerical features. 🤗 models included! What's the best? Check out our blog post to find out 👀 skrub-data.org/skrub-materi...
skrub-data.org
What’s the best way to encode categorical features? A use case with Skrub encoders – Skrub learning materials
072
Kevin Markham @dataschool.io · 24/03/2025
Just finished recording my new AI course 😅 Sign up for early access: dataschool.kit.com/agents
110
Reposted by Kevin Markham
Duc Nguyen Huu @ducnh279.bsky.social · 18/03/2025
Many good advices/best practices for missing value imputation in the paper! I now have a much deeper appreciation for Data School's course and regard it as the best scikit-learn course. Master Machine Learning with scikit-learn: courses.dataschool.io/master-machi...
courses.dataschool.io
Course: Master Machine Learning with scikit-learn
Get ready for your dream job in Machine Learning!
121
Kevin Markham @dataschool.io · 17/03/2025
In honor of March Madness 🏀, I've got a new blog post: www.dataschool.io/pandas-strea... Learn how to identify & analyze scoring streaks using pandas operations: - shift() - cumsum() - boolean math - groupby()
dataschool.io
How to calculate "scoring streaks" with pandas 🏀
Learn how to identify & analyze consecutive events in your data using advanced DataFrame methods!
011
Kevin Markham @dataschool.io · 13/03/2025
"To Type or Not to Type?" is an excellent introduction (and reference guide) to type hints in Python: blog.jonathanchun.com/2025/02/16/t...
030
Kevin Markham @dataschool.io · 13/03/2025
"Some people today are discouraging others from learning programming on the grounds AI will automate it. This advice will be seen as some of the worst career advice ever given." -- Andrew Ng, legendary AI researcher Source: www.deeplearning.ai/the-batch/is...
deeplearning.ai
DeepSeek-R1 Uncensored, QwQ-32B Puts Reasoning in Smaller Model, and more...
The Batch AI News and Insights: Some people today are discouraging others from learning programming on the grounds AI will automate it.
011
Reposted by Kevin Markham
Simon Willison @simonwillison.net · 11/03/2025
Here's the table of contents for my lengthy new piece on how I use LLMs to help me write code simonwillison.net/2025/Mar/11/...
If someone tells you that coding with LLMs is easy they are (probably unintentionally) misleading you. They may well have stumbled on to patterns that work, but those patterns do not come naturally to everyone.

I’ve been getting great results out of LLMs for code for over two years now. Here’s my attempt at transferring some of that experience and intution to you.

Set reasonable expectations
Account for training cut-off dates
Context is king
Ask them for options
Tell them exactly what to do
You have to test what it writes!
Remember it’s a conversation
Use tools that can run the code for you
Vibe-coding is a great way to learn
A detailed example
Be ready for the human to take over
The biggest advantage is speed of development
LLMs amplify existing expertise
Bonus: answering questions about codebases
1433467
Kevin Markham @dataschool.io · 05/03/2025
These are @simonwillison.net's current favorite AI models for Python programming: - Claude 3.7 Sonnet with thinking turned on - OpenAI's o3-mini-high - GPT-4o with Code Interpreter Source: simonwillison.net/2025/Mar/2/h...
simonwillison.net
Hallucinations in code are the least dangerous form of LLM mistakes
A surprisingly common complaint I see from developers who have tried using LLMs for code is that they encountered a hallucination—usually the LLM inventing a method or even a full …
010
Kevin Markham @dataschool.io · 04/03/2025
19 professionals (in a variety of fields) evaluated OpenAI's Deep Research vs Google's Deep Research. OpenAI was the clear winner 🏆 Neat study by @binarybits.bsky.social, read more here: www.understandingai.org/p/these-expe...
043
Kevin Markham @dataschool.io · 04/03/2025
"The next time someone predicts that we will soon have AI that can do anything 'a human can do', ask them what they think a human can do. You may find that they are only considering capabilities that are easily measured." Source: amistrongeryet.substack.com/p/where-ai-f...
amistrongeryet.substack.com
If AGI Means Everything People Do... What is it That People Do?
And Why Are Today’s "PhD" AIs So Hard To Apply To Everyday Tasks?
020
Reposted by Kevin Markham
Trey Hunner @trey.io · 03/03/2025
A couple months ago @dataschool.io wrote about a tool he uses to chat with different LLM models without paying a monthly subscription to all of them. The tool is called Typing Mind and I decided to pay $30 for lifetime access. It was well worth it. Kevin's post 👇 www.dataschool.io/save-money-o...
dataschool.io
Use premium AI models for pennies 💰
Learn how to access ChatGPT, Claude, and more for pennies per conversation rather than paying for expensive subscriptions!
442
Reposted by Kevin Markham
Kevin Markham @dataschool.io · 30/01/2025
Want to keep up with the latest developments in AI? Check out the 7 newsletters I personally read & recommend for AI news, insights, and analysis: 👉 www.dataschool.io/best-ai-news... 👈 Includes: @simonwillison.net @emollick.bsky.social @sebastianraschka.com @binarybits.bsky.social
dataschool.io
How to keep up with AI in 2025 🏃‍♂️
These 7 AI experts will guide you through the most important developments in Artificial Intelligence.
3143
Kevin Markham @dataschool.io · 22/02/2025
@gruber.foo Do your friends & family know you invented Markdown? Because it's pretty cool that something you made is used so heavily by LLMs, which is arguably the most important innovation in technology today.
010
Kevin Markham @dataschool.io · 16/02/2025
Here's my personal guide to Bluesky happiness 🌈 1. Be very selective about who I follow (42 people at the moment) 2. Read everything in the "Following" feed, and nothing else 3. Trust that the people I follow will surface other good people to follow 4. Unfollow anyone who no longer makes the cut
011
Kevin Markham @dataschool.io · 12/02/2025
Wondering about the differences between "Jupyter", "Jupyter Notebook", "JupyterLab", "IPython", "Colab", and other related terms? I'll explain these terms (and more) in 5 minutes: ▶️ www.youtube.com/watch?v=TDlG...
youtube.com
Jupyter & IPython terminology explained
YouTube video by Data School
021
Kevin Markham @dataschool.io · 07/02/2025
Economist Tyler Cowen on OpenAI's Deep Research: "I think of the quality as comparable to having a good PhD-level research assistant, and sending that person away with a task for a week or two, or maybe more." marginalrevolution.com/marginalrevo...
marginalrevolution.com
Deep Research - Marginal REVOLUTION
I have had it write a number of ten-page papers for me, each of them outstanding.  I think of the quality as comparable to having a good PhD-level research assistant, and sending that person away with...
000
Kevin Markham @dataschool.io · 07/02/2025
Comparing: - Software Developers - ML Engineers - LLM Developers - Prompt Engineers Read here: www.louisbouchard.ai/llm-develope... Image & article by Louis-François Bouchard
011