Sign up to get notified when it's available: https://dataschool.kit.com/mlbook

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, demonstrate its killer feature of chatting with multiple models side-by-side, and explain when paying for a subscription is actually the smarter choice. Get API keys from... OpenAI: https://platform.openai.com/api-keys Claude: https://console.anthropic.com/settings/keys Google: https://aistudio.google.com/app/apikey TypingMind: https://www.typingmind.com/ My new Machine Learning book: https://dataschool.kit.com/mlbook Timestamps: 0:00 Introduction 0:37 Pay-per-token 1:18 Setup part 1: API keys 2:14 Setup part 2: TypingMind 3:02 Cost examples 4:05 Chatting with multiple models 5:36 Disadvantages of pay-per-token 6:31 TypingMind Premium 7:24 My Machine Learning 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: 👉👉 https://dataschool.kit.com/mlbook 👈👈 This is a dream come true, so I'd love your support! 💫 Please enter your email at the link above, and share with a friend! Thank you again 🙏

This week in AI: Veo 3 makes a TV ad, ChatGPT saves your deleted chats, Midjourney gets sued, Google talks AGI, and Copilot patches a huge security flaw. Sources: Kalshi ad: https://www.youtube.com/watch?v=-QMftwmyW-A Kalshi ad creator's post: https://x.com/PJaccetturo/status/1932893260399456513 OpenAI's response to court order: https://openai.com/index/response-to-nyt-data-demands/ Sam Altman's post: https://x.com/sama/status/1930785056194539779 Wired story on Disney lawsuit: https://www.wired.com/story/disney-universal-sue-midjourney/ Disney lawsuit PDF: https://www.documentcloud.org/documents/25971036-disney-v-midjourney/ Sundar Pichai interview: https://www.youtube.com/watch?v=9V6tWC4CdFQ Aim's post on Copilot security: https://www.aim.security/lp/aim-labs-echoleak-blogpost 0:00 AI-generated TV ad airs during NBA finals 0:33 Court orders OpenAI to retain user chats 1:07 Disney & Universal sue Midjourney 1:38 Google CEO: AGI by 2030? 2:06 Security vulnerability in Microsoft 365 Copilot

This is a lesson from my new course, Build AI agents with Python: https://courses.dataschool.io/build-ai-agents-with-python 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 Further reading: https://python.langchain.com/docs/tutorials/rag/ Thumbnail image credit: LangChain

Are you trying to understand the differences between Jupyter Notebook, JupyterLab, IPython, Colab, and other related terms? You're in the right place! This video is also available as a blog post: https://www.dataschool.io/jupyter-and-ipython-terminology/ Links from the video: IPython: https://ipython.readthedocs.io/en/stable/ Jupyter Notebook: https://jupyter-notebook.readthedocs.io/en/latest/ JupyterLab: https://jupyterlab.readthedocs.io/en/latest/ Jupyter kernels: https://github.com/jupyter/jupyter/wiki/Jupyter-kernels JupyterLab Desktop: https://github.com/jupyterlab/jupyterlab-desktop JupyterLite: https://github.com/jupyterlite/jupyterlite Google Colab: https://colab.research.google.com/ Kaggle Code: https://www.kaggle.com/code Deepnote: https://deepnote.com/

AI is moving incredibly FAST. I'll show you the 7 best sources I follow to keep up with the most important developments in AI. This video is also available as a blog post: https://www.dataschool.io/best-ai-newsletters-in-2025/ Links from the video: 2024 AI timeline: https://huggingface.co/spaces/reach-vb/2024-ai-timeline The Neuron: https://sparklp.co/p/8d06bb74cf (affiliate link) The Batch: https://www.deeplearning.ai/the-batch/ Simon Willison's blog: https://simonwillison.net/ Things we learned about LLMs in 2024: https://simonwillison.net/2024/Dec/31/llms-in-2024/ One Useful Thing: https://www.oneusefulthing.org/ Ahead of AI: https://magazine.sebastianraschka.com/ Noteworthy AI Research Papers of 2024 (Part One): https://magazine.sebastianraschka.com/p/ai-research-papers-2024-part-1 Noteworthy AI Research Papers of 2024 (Part Two): https://magazine.sebastianraschka.com/p/ai-research-papers-2024-part-2 Understanding AI: https://www.understandingai.org/ LLMs explained with a minimum of math and jargon: https://www.understandingai.org/p/large-language-models-explained-with Am I Stronger Yet?: https://amistrongeryet.substack.com/ Are We on the Brink of AGI?: https://amistrongeryet.substack.com/p/are-we-on-the-brink-of-agi

Watch the first two lessons of my new course, Build an AI chatbot with Python ($9): https://courses.dataschool.io/build-an-ai-chatbot-with-python In this video, you'll learn: - What is a Large Language Model (LLM)? - How are LangChain and LangGraph used to build AI apps? - What are my recommendations for free and cheap LLMs? Resources: LangChain: https://python.langchain.com/docs/introduction/ LangGraph: https://langchain-ai.github.io/langgraph/ OpenAI API pricing: https://openai.com/api/pricing/ OpenAI tokenizer: https://platform.openai.com/tokenizer Free LLM API resources: https://github.com/cheahjs/free-llm-api-resources

Guess the topic of my new course, and on Friday I'll randomly select TWO people who were correct to get a FREE copy of the course. Good luck! 🤞 Here are my current courses: https://courses.dataschool.io

This is the outline of my NEW course, "Master Machine Learning with scikit-learn." You can enroll here: https://courses.dataschool.io/master-machine-learning-with-scikit-learn For all paid courses, I offer location-based discounts (up to 75%) to people in 160+ countries. Check your discount here: https://courses.dataschool.io/discounts Enroll in a FREE Data Science course here: https://courses.dataschool.io/free-courses

This is the overview of my NEW course, "Master Machine Learning with scikit-learn." You can enroll here: https://courses.dataschool.io/master-machine-learning-with-scikit-learn For all paid courses, I offer location-based discounts (up to 75%) to people in 160+ countries. Check your discount here: https://courses.dataschool.io/discounts Enroll in a FREE Data Science course here: https://courses.dataschool.io/free-courses

Learn the how & why of "ensembling", the surprisingly simple way to make better Machine Learning predictions! P.S. This is a lesson from my NEW course, "Master Machine Learning with scikit-learn." You can enroll here: https://courses.dataschool.io/master-machine-learning-with-scikit-learn For all paid courses, I offer location-based discounts (up to 75%) to people in 160+ countries. Check your discount here: https://courses.dataschool.io/discounts Enroll in a FREE Data Science course here: https://courses.dataschool.io/free-courses

If you need to save a Pipeline with custom transformers, you’ll have to define the functions it depends upon in the new environment. In this lesson, you’ll learn how avoid that burden by using the cloudpickle library. P.S. This is a lesson from my NEW course, "Master Machine Learning with scikit-learn." You can enroll here: https://courses.dataschool.io/master-machine-learning-with-scikit-learn For all paid courses, I offer location-based discounts (up to 75%) to people in 160+ countries. Check your discount here: https://courses.dataschool.io/discounts Enroll in a FREE Data Science course here: https://courses.dataschool.io/free-courses

By default, the cross_val_score function in scikit-learn does not shuffle samples. In this lesson, you’ll learn when you might need to shuffle and how to do it. P.S. This is a lesson from my NEW course, "Master Machine Learning with scikit-learn." You can enroll here: https://courses.dataschool.io/master-machine-learning-with-scikit-learn For all paid courses, I offer location-based discounts (up to 75%) to people in 160+ countries. Check your discount here: https://courses.dataschool.io/discounts Enroll in a FREE Data Science course here: https://courses.dataschool.io/free-courses

If your dataset has significant class imbalance, the "cost" may differ between the two types of prediction errors. In this lesson, you’ll learn how to use cost-sensitive learning to adjust the model to better match your priorities. P.S. This is a lesson from my NEW course, "Master Machine Learning with scikit-learn." You can enroll here: https://courses.dataschool.io/master-machine-learning-with-scikit-learn For all paid courses, I offer location-based discounts (up to 75%) to people in 160+ countries. Check your discount here: https://courses.dataschool.io/discounts Enroll in a FREE Data Science course here: https://courses.dataschool.io/free-courses