A man spends 50 years teaching at MIT.
He knows his time is running out.
So he records one last lecture — everything he knows, distilled into a single hour.
He died 5 months later.
This is that lecture.
The most important hour you'll watch this week. 👇
Bookmark it for later
That's a wrap! Over the next 24 days, I'm sharing the 24 concepts that helped me become a data scientist.
If you enjoyed this thread:
1. Follow me @mdancho84 for more of these
2. RT the tweet below to share this thread with your audience
How to use AI to learn anything faster
__________
P.S. Try Radiant. It captures your meetings without a bot, then drafts your follow-up emails for you.
https://t.co/8QhALLSQZi
X'te amit: "$NVDA TRUMP ON NVIDIA’S $500B INVESTMENT IN THE USA: “I want to thank Jensen. Nvidia is an amazing American company. They wouldn’t have done this without the tariffs.”" / X https://t.co/lz9XM6OZd7
$NVDA
TRUMP ON NVIDIA’S $500B INVESTMENT IN THE USA:
“I want to thank Jensen. Nvidia is an amazing American company. They wouldn’t have done this without the tariffs.”
This link contains Tutorials + Books + Courses + Trainings + Educational Resources in:
- Data science
- Python
- Artificial Intelligence
- BIG DATA
- Data Analytics
- Google Cloud Platform
- IT Training
- MBA
- Cybersecurity
And much more
Check this Google drive link: https://t.co/gISNvRmob8
Share this! Someone on your TL might need this.
Mastering Memory Management: From Manual Cleanup to Smart Pointers in C/C++
In this post, we’ll explore the intricacies of memory management, discuss why garbage collection isn’t typically used in C/C++, and see into alternative approaches for efficient memory handling.
Essential tools in the 2025 AI agent stack
(bookmark to save for later)
Framework
- @pyautogen AG2: end-to-end multi-agent automation platform
- @crewAIInc: Faster, simple, powerful multi-agent framework
- @LiteLLM: Call 100+ LLMs with a single library
Monitoring
- @AgentOpsAI: Leading AI agent platform observability platform
Search
- @firecrawl: Turn websites into LLM-ready data
- @perplexity_ai: AI powered search engine
- @ExaAILabs: Business-grade search and crawling for any web data
External APIs
- @composio: 250+ tools ready to connect to agents
- @stripe: Add usage billing to any AI agent
Computer Use
- @browserbase: Easy to use web browsers for your agents
- @OpenInterpreter: Give your AI agents control over your computer's terminal
Memory
- @mem0ai: Advanced memory management for any agent
- @neondatabase: Serverless postgres with easy RAG baked in
Which ones did I miss?
ML Books I'll Be Reading in 2025 📚
1. "AI Engineering: Building Applications with Foundation Models" (Huyen, 2024): https://t.co/WILuuT4XqD
We’ll probably read it in the study group "AI from Scratch."
2. "Alice’s Adventures in a Differentiable Wonderland: A Primer on Designing Neural Networks (Volume I)"(Scardapane, 2024): https://t.co/Rt7229ofMa
Looks sweet and short, and I’ve been wanting to read it for a while.
3. "Writing for Developers: Blogs That Get Read" (Sarna and Dunlop, 2025): https://t.co/xTrSLAeQ2r
Not ML-related, but still relevant.
4. "Pen & Paper Exercises in Machine Learning"(Gutmann, 2022): https://t.co/SvIlAWQNfx
I’m not sure if I’ll go through the whole book, but it looks fun—maybe also for a study group?
5. "Fundamentals of Data Engineering: Plan and Build Robust Data Systems" (Reis, Housley, 2022): https://t.co/Ol1Kc2E3yq
Not ML-related, but still relevant.
6. "Large Language Models: A Deep Dive—Bridging Theory and Practice" (Kamath et al., 2024): https://t.co/YYOQZESR5d
This one is probably too long and expensive, but I want to get it haha.
Anything else to add?
Agents are just like other pieces of software
- have workflows
- need to be deployed and monitored
- have to transform and understand data (big at times)
- have different UX widgets that can visualize information
- Git is in C
- Vim is in C
- Linux is in C
- macOS is in C
- MySQL is in C
- CPython is in C
- Windows is in C
- Photoshop/GIMP in C
In 2025, are you still searching from where to learn C?
You can create an AI Agent that answers your email with a few clicks.
1. Go to ChatLLM (https://t.co/4bUPshCQef)
2. Click on AI Engineer
3. Select Create an AI Agent
4. Choose the Email Answering Agent
ChatLLM will do the rest: it will code, test, and deploy the agent for you.
You can also create a custom agent in English.
The Agent Economy is coming (somebody should write a book and use this title.) We are going to see examples like this, times 1,000 in 2025.
Just think about how many repetitive tasks you perform every day. Some of these tasks are involved enough that we couldn't automate them with pre-AI solutions.
That's where we'll see agents explode, and I'm here for it.