The Underfitted

"The model will converge anyway" - a compelling argument, and a costly misconception. Two models. Same everything. Model A, step 0: loss = 3.29 → starts learning immediately. Model B, step 0: loss = 27 → spends the first 9,000 steps just getting back to where A started. Model B didn't train for 10k steps. It trained for ~800. The rest was debt repayment. A bad initialization doesn't slow you down. It steals your training budget — silently, one "optimization" step at a time. 🧵

@CodeEdison if it were that simple

math & statistics ↓ python ↓ numpy / pandas / matplotlib ↓ data preprocessing & feature engineering ↓ classical ml ↓ model evaluation & metrics ↓ advanced ml ↓ nlp fundamentals ↓ deep learning ↓ pytorch / tensorflow ↓ cnn / rnn ↓ transformers ↓ llms (openai / gemini / claude) ↓ prompt engineering ↓ embeddings & vector databases ↓ rag (retrieval augmented generation) ↓ langchain ↓ langgraph ↓ mcps / tool calling ↓ agents & agentic workflows ↓ finetuning ↓ inference optimization ↓ fastapi ↓ model deployment ↓ monitoring & cost optimization congrats you're an AI engineer now

@romerojr__ @claudeai Appreciate!

@SimplySigmoid @claudeai dope picture - good luck with your studies!!

Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.

@tetsuoai king

Andrej Karpathy on neural nets. loss functions, backprop, gradient descent.

@vivoplt Also dont forget about this gem

The best YouTube channels to learn AI from scratch 1. Andrej Karpathy 2. 3Blue1Brown 3.Stanford CS229 (Andrew Ng) 4.Machine Learning Street Talk 5. StatQuest 6. Serrano Academy 7. Jeremy Howard 8. Hamel Husain 9.Dave Ebbelaar 10. Lex Fridman

@BTechWalaBanda @karthikponna19 help with?

@SimplySigmoid @karthikponna19 Can you help me in this I'm also interested in this role...

finally joined as an AI Engineer at a healthcare company

ITS BEEN 2 HOURS AND CLAUDE REMAINS DOWN!

@vivoplt having a good foundation is a true leverage in this AI era

Best YouTube Channels To Learn in 2026 1. Cybersecurity – John Hammond 2. Artificial Intelligence – Andrej Karpathy 3. AI Research Breakdown – Yannic Kilcher 4. Web Development – The Net Ninja 5. Python Programming – Corey Schafer 6. DevOps – TechWorld with Nana 7. Cloud Computing – AWS re:Invent 8. Data Analytics – Luke Barousse 9. System Design – Gaurav Sen 10. Databases – Hussein Nasser 11. Low-Level Programming – The Cherno 12. Linux – Learn Linux TV 13. Networking – David Bombal 14. Math for ML – 3Blue1Brown

It's 6PM on a Saturday. Karpathy on screen. Handwritten notes on the desk. VS Code open with makemore_from_scratch. No tutorial. No shortcut. Just activation functions, neuron flow through layers, and the slow satisfaction of actually understanding what's happening inside the network. Week by week. Layer by layer.

@Shivam25mishra you need solid foundation to build your house

Why do colleges focus more on theory than building real projects?

@Shruti_0810 dont forget about this GEM

This is insane 😳 Everyone is using AI tools. Very few actually understand what’s happening under the hood. So I went deep. I collected Stanford’s full LLM curriculum and structured it into a clean, step-by-step learning path anyone can follow. No fluff. No random YouTube hopping. Just a proper roadmap: • Transformers • Pre-training • Fine-tuning • Alignment • Agents • Evaluation If you study this once, you’ll stop “guessing prompts” and start thinking like a real AI engineer. I’ll drop the link in the comments

@VadimStrizheus thats what a single prompt could do

this is what a company looks like in 2026. not people. not offices. not salaries. a folder. .claude/agents/ engineering/ marketing/ design/ ops/ testing/ every role. every department. every function. all .md files. i have 12 of these running in OpenClaw right now. the org chart is dead. the directory is the new company.

@quantscience_ if would be that simple

Automate your trading strategies in Python How to build your first trading bot: (a thread)

@anthdm quants era incoming

What if I told you that you never need to manual mock up your charts again? MMT will be the first agentic charting platform on planet earth.

@elonmusk better than my automated system

Prediction of the future is the best measure of intelligence

@bigaiguy a comprehensive transformer breakdown by Claude

@SimplySigmoid What are you showing me here? Lol

🚨 BREAKING: AI can now teach machine learning like Stanford's CS229 professors (for free). Here are 15 insane Claude prompts that replace $120,000 ML bootcamps (Save for later)

@nalinrajput23 math

- Programming sits on maths. - Algorithms run on maths. - Every AI model is maths. - Machine learning is maths. - Deep learning is maths. - Graphics are maths. - Simulations are maths. - Cryptography is maths. - Blockchain is maths. - Data science is maths. - Optimization is maths. - Signal processing is maths. - Robotics moves because of maths. - Game engines run because of maths. - Your entire tech stack survives on maths. You're still asking if we need math for programming?