Skip to content

amitness/learning

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1,107 Commits
LICENSE
LICENSE
 
 
README.md
README.md
 
 

Repository files navigation

learning

A running log of things I'm learning to build strong core software engineering skills while also expanding my knowledge of adjacent technologies a little bit everyday.

Updated: Once a month | Current Focus: Generative AI

Core Skills

Generic skills that are transferrable to any sort of software work I do

Python Programming

Resource Progress
Datacamp: Writing Efficient Python Code ✅
Datacamp: Writing Functions in Python ✅
Datacamp: Object-Oriented Programming in Python ✅
Datacamp: Intermediate Object-Oriented Programming in Python ✅
Datacamp: Importing Data in Python (Part 1) ✅
Datacamp: Importing Data in Python (Part 2) ✅
Datacamp: Intermediate Python for Data Science ✅
Datacamp: Python Data Science Toolbox (Part 1) ✅
Datacamp: Python Data Science Toolbox (Part 2) ✅
Datacamp: Developing Python Packages ✅
Datacamp: Conda Essentials ✅
Youtube: Tutorial: Sebastian Witowski - Modern Python Developer's Toolkit ✅
Datacamp: Working with Dates and Times in Python ✅
Datacamp: Command Line Automation in Python ⬜
Book: Python 201 ⬜
Book: Writing Idiomatic Python 3 ⬜
Article: Python's many command-line utilities ⬜
Article: A Programmer’s Introduction to Unicode ⬜
Article: Exposing string types to maximize user happiness ✅

Testing & Profiling

Resource Progress
Datacamp: Unit Testing for Data Science in Python ✅
Book: Test Driven Development with Python ⬜
Article: Introduction to Memory Profiling in Python ✅
Article: Profiling Python code with memory_profiler ✅
Article: How to Use "memory_profiler" to Profile Memory Usage by Python Code? ✅
Youtube: Debug Python inside Docker using debugpy and VSCode ✅
Article: Concurrency For Starlette Apps (e.g FastAPI / FastHTML) ✅

Data Structures and Algorithms

Resource Progress
Book: Grokking Algorithms ✅
Book: The Tech Resume Inside Out ✅
Neetcode: Algorithms and Data Structures for Beginners ✅
Neetcode: Advanced Algorithms 1/7 ⬜
Udacity: Intro to Data Structures and Algorithms ✅
Youtube: Sliding Window Technique - Algorithmic Mental Models 36:44 ✅

Linux & Command Line

Resource Progress
Datacamp: Introduction to Shell for Data Science ✅
Datacamp: Introduction to Bash Scripting ✅
Datacamp: Data Processing in Shell ✅
MIT: The Missing Semester ✅
Udacity: Linux Command Line Basics ✅
Udacity: Shell Workshop ✅
Udacity: Configuring Linux Web Servers ✅

Version Control

Resource Progress
Udacity: Version Control with Git ✅
Datacamp: Introduction to Git for Data Science ✅
Udacity: GitHub & Collaboration ✅
Udacity: How to Use Git and GitHub ✅
Youtube: How to Use Git Worktree | Checkout Multiple Git Branches at Once ✅
Datacamp: Advanced Git ✅

Databases

Resource Progress
Udacity: Intro to relational database ✅
Udacity: Database Systems Concepts & Design ⬜
Datacamp: Database Design ✅
Datacamp: Introduction to Databases in Python ⬜
Datacamp: Intro to SQL for Data Science ✅
Datacamp: Intermediate SQL ✅
Datacamp: Joining Data in SQL ✅
Datacamp: Data Manipulation in SQL ⬜
Udacity: SQL for Data Analysis ⬜
Datacamp: Exploratory Data Analysis in SQL ⬜
Datacamp: Applying SQL to Real-World Problems ⬜
Datacamp: Analyzing Business Data in SQL ⬜
Datacamp: Reporting in SQL ⬜
Datacamp: Data-Driven Decision Making in SQL ⬜
Datacamp: NoSQL Concepts ✅
Datacamp: Introduction to MongoDB in Python ⬜

System Design

Resource Progress
Book: Designing Machine Learning Systems ✅
Neetcode: System Design for Beginners ✅
Neetcode: System Design Interview ✅
Datacamp: Customer Analytics & A/B Testing in Python ✅
Datacamp: A/B Testing in Python ⬜
Udacity: A/B Testing ⬜
Datacamp: MLOps Concepts ✅
Datacamp: Machine Learning Monitoring Concepts ✅
Udacity: Authentication & Authorization: OAuth ✅
Udacity: HTTP & Web Servers ✅
Udacity: Client-Server Communication ⬜
Udacity: Designing RESTful APIs ✅
Udacity: Networking for Web Developers ✅

Maths

Resource Progress
Datacamp: Foundations of Probability in Python ✅
Datacamp: Introduction to Statistics ✅
Datacamp: Introduction to Statistics in Python ✅
Datacamp: Hypothesis Testing in Python ✅
Datacamp: Statistical Thinking in Python (Part 1) ✅
Datacamp: Statistical Thinking in Python (Part 2) ✅
Datacamp: Experimental Design in Python ✅
Datacamp: Practicing Statistics Interview Questions in Python ⬜
edX: Essential Statistics for Data Analysis using Excel ✅
Udacity: Intro to Inferential Statistics ✅
MIT 18.06 Linear Algebra, Spring 2005 ✅
Udacity: Eigenvectors and Eigenvalues ✅
Udacity: Linear Algebra Refresher ⬜
Youtube: Essence of linear algebra ⬜

Specialization

Traditional Machine Learning

Resource Progress
Book: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition ⬜
Book: A Machine Learning Primer ✅
Book: Grokking Machine Learning ✅
Book: The StatQuest Illustrated Guide To Machine Learning ✅
Datacamp: Ensemble Methods in Python ✅
Datacamp: Extreme Gradient Boosting with XGBoost ⬜
Datacamp: Clustering Methods with SciPy ✅
Datacamp: Unsupervised Learning in Python ✅
Udacity: Segmentation and Clustering ✅
Datacamp: Intro to Python for Data Science ✅
edX: Implementing Predictive Analytics with Spark in Azure HDInsight ✅
Datacamp: Supervised Learning with scikit-learn ✅
Datacamp: Machine Learning with Tree-Based Models in Python ✅
Datacamp: Linear Classifiers in Python ✅
Datacamp: Model Validation in Python ✅
Datacamp: Hyperparameter Tuning in Python ✅
Datacamp: HR Analytics in Python: Predicting Employee Churn ✅
Datacamp: Predicting Customer Churn in Python ✅
Datacamp: Dimensionality Reduction in Python ✅
Datacamp: Preprocessing for Machine Learning in Python ✅
Datacamp: Data Types for Data Science ✅
Datacamp: Cleaning Data in Python ✅
Datacamp: Feature Engineering for Machine Learning in Python ✅
Datacamp: Predicting CTR with Machine Learning in Python ✅
Datacamp: Intro to Financial Concepts using Python ✅
Datacamp: Fraud Detection in Python ✅
Article: The wrong batch size is all it takes ✅
Article: A Gentle Introduction to Expectation-Maximization (EM Algorithm) ✅
Article: How to Use Out-of-Fold Predictions in Machine Learning ✅
Article: Stacking and Blending — An Intuitive Explanation ✅

Deep Learning

Resource Progress
Article: An overview of gradient descent optimization algorithms ✅
Book: Make Your Own Neural Network ✅
Fast.ai: Practical Deep Learning for Coder (Part 1) ✅
Fast.ai: Practical Deep Learning for Coder (Part 2) 9, 13,14,17,18(48:10),19 ⬜
Datacamp: Convolutional Neural Networks for Image Processing ✅
Karpathy: Neural Networks: Zero to Hero ✅
Article: Weight Initialization in Neural Networks: A Journey From the Basics to Kaiming ⬜
Article: Things that confused me about cross-entropy ✅
Article: Why is the ReLU function not differentiable at x=0? ✅
Article: Are CNNs invariant to translation, rotation, and scaling? ✅
Article: How to Control the Stability of Training Neural Networks With the Batch Size ✅
Article: A Visual Guide to Learning Rate Schedulers in PyTorch ✅

Natural Language Processing

Resource Progress
Book: Natural Language Processing with Transformers ✅
Stanford CS224U: Natural Language Understanding | Spring 2019 15/15 lectures ✅
Stanford CS224N: Stanford CS224N: NLP with Deep Learning | Winter 2019 22/22 lectures ✅
CMU: Low-resource NLP Bootcamp 2020 8/8 lectures ✅
CMU Multilingual NLP 2020 ✅
Datacamp: Feature Engineering for NLP in Python ✅
Datacamp: Natural Language Processing Fundamentals in Python ✅
Datacamp: Regular Expressions in Python ✅
Datacamp: RNN for Language Modeling ✅
Datacamp: Natural Language Generation in Python ✅
Datacamp: Building Chatbots in Python ✅
Datacamp: Sentiment Analysis in Python ✅
Datacamp: Machine Translation in Python ✅
Article: The Unreasonable Effectiveness of Collocations ⬜
Article: FuzzyWuzzy: Fuzzy String Matching in Python ✅
Article: Transformers: Origins ⬜
Notebook: Understanding the Difference Between Embedding Layers and Linear Layers ✅

Generative AI

LLM Theory

Resource Progress
Book: Hands-On Large Language Models: Language Understanding and Generation ✅
Book: AI Engineering: Building Applications with Foundation Models ✅
Book: Designing Large Language Model Applications ⬜
Book: Large Language Models: A Deep Dive: Bridging Theory and Practice ⬜
Book: Super Study Guide: Transformers & Large Language Models ✅
Book: The Hundred-Page Language Models Book ✅
Book: Build a Large Language Model (From Scratch) 246/581
The Smol Training Playbook: The Secrets to Building World-Class LLMs ⬜
Article: You could have designed state of the art Positional Encoding ✅
Article: From Digits to Decisions: How Tokenization Impacts Arithmetic in LLMs ✅
Article: SolidGoldMagikarp (plus, prompt generation) ✅
Article: Sampling for Text Generation ✅
Article: First Token Cutoff LLM sampling ✅
Article: The Big LLM Architecture Comparison ✅
Article: From GPT-2 to gpt-oss: Analyzing the Architectural Advances ✅
Article: A Visual Guide to Mamba and State Space Models ⬜
Article: Patterns and Messages - Part 1 - The Missing Subscript ✅
Article: How text diffusion works ✅
Article: The Illustrated Evo 2 ⬜
Article: Interpreting the Prediction of BERT Model for Text Classification ✅
Article: 2025: The year in LLMs ✅
DeepLearning.AI: Pretraining LLMs ✅
DeepLearning.AI: Reinforcement Learning from Human Feedback ✅
DeepLearning.AI: How Transformer LLMs Work ✅
Karpathy: Intro to Large Language Models 1hr ✅
Karpathy: Let's build the GPT Tokenizer 2hr13m ✅
Karpathy: Let's reproduce GPT-2 (124M) 4hr1m ✅
Youtube: A Hackers' Guide to Language Models 1hr30m ✅
Karpathy: Deep Dive into LLMs like ChatGPT 3h31m ✅
Youtube: 5 Years of GPTs with Finbarr Timbers 55m ✅
Youtube: Stanford CS229 I Machine Learning I Building Large Language Models (LLMs) 1h44m ✅
Youtube: LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU 1h10m ✅
Youtube: CMU Advanced NLP Fall 2024 (14): Ensembling and Mixture of Experts ✅
Youtube: A little guide to building Large Language Models in 2024 1h15m ✅
Youtube: How to approach post-training for AI applications 22m ✅
Youtube: How I use LLMs 2h7m ✅
Youtube: Simple Diffusion Language Models ✅
Youtube: Zed Inferred: Diffusion Language Models ✅

Post-training (RLHF / RLVR)

Resource Progress
Book: A Little Bit of Reinforcement Learning from Human Feedback ✅
Course: Post-training of LLMs ✅
Article: Scaling test-time compute - a Hugging Face Space by HuggingFaceH4 ✅
Article: DeepSeek R1's recipe to replicate o1 and the future of reasoning LMs ✅
Article: The Illustrated DeepSeek-R1 ✅
Article: A Visual Guide to Reasoning LLMs ✅
Article: GRPO in DeepSeek-R1 ✅
Youtube: How DeepSeek Changes the LLM Story ✅
Youtube: Speculations on Test-Time Scaling (o1) 47m ✅
Youtube: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 1h19m ✅
Youtube: MIT EI seminar, Hyung Won Chung from OpenAI. "Don't teach. Incentivize." 35m ✅
Youtube: Group Relative Policy Optimization (GRPO) - Formula and Code 24m ✅

Multi-modality (Vision)

Resource Progress
Article: Understanding Multimodal LLMs ✅
Article: Computer-Using Agent ✅
Article: Flow Matching in 5 Minutes ✅
Article: Understanding Patch Embeddings for Vision Transformers (ViT) ✅
Youtube: AI Visions Live | Merve Noyan | Open-source Multimodality 54m ✅
DeepLearning.AI: How Diffusion Models Work ✅
DeepLearning.AI: Prompt Engineering for Vision Models ⬜
DeepLearning.AI: Building Multimodal Search and RAG ✅
Pinecone: Embedding Methods for Image Search 0/8
Youtube: Lesson 9A 2022 - Stable Diffusion deep dive ✅
Article: Diffusion models are autoencoders ✅
Article: Diffusion Language Models ✅
Article: Guidance: a cheat code for diffusion models ✅
Article: Perspectives on diffusion ✅
Article: The geometry of diffusion guidance ✅
Article: Diffusion is spectral autoregression ✅
Article: Generative modelling in latent space ✅
Youtube: Sander Dieleman - Generative modelling through iterative refinement ✅

Multi-modality (Audio)

Resource Progress
Article: Speech AI models: an introduction ⬜
Article: Voice AI & Voice Agents - An Illustrated Primer ⬜
Article: Neural audio codecs: how to get audio into LLMs ⬜

Information Retrieval / RAG

Resource Progress
Article: Pretrained Transformer Language Models for Search - part 1 ✅
Article: Pretrained Transformer Language Models for Search - part 2 ✅
Article: Pretrained Transformer Language Models for Search - part 3 ✅
Article: Pretrained Transformer Language Models for Search - part 4 ✅
Article: How not to use BERT for Document Ranking ✅
Article: Understanding LanceDB's IVF-PQ index ✅
Article: A little pooling goes a long way for multi-vector representations ✅
Article: Levels of Complexity: RAG Applications ✅
Article: Systematically Improving Your RAG ✅
Article: Stop using LGTM@Few as a metric (Better RAG) ✅
Article: Low-Hanging Fruit for RAG Search ✅
Article: What AI Engineers Should Know about Search ✅
Article: Evaluating Chunking Strategies for Retrieval ✅
Article: Sentence Embeddings. Introduction to Sentence Embeddings ✅
Article: LambdaMART in Depth ⬜
Article: Guided Generation with Outlines ✅
Article: RAG tricks from the trenches ⬜
Article: Retrieval 101 ⬜
Article: Understanding the BM25 full text search algorithm ⬜
Arxiv: Ragas: Automated Evaluation of Retrieval Augmented Generation ✅
Course: Fullstack Retrieval ⬜
Course: The RAG Flywheel ⬜
DeepLearning.AI: Building and Evaluating Advanced RAG Applications ✅
DeepLearning.AI: Vector Databases: from Embeddings to Applications ✅
DeepLearning.AI: Advanced Retrieval for AI with Chroma ✅
DeepLearning.AI: Prompt Compression and Query Optimization ✅
DeepLearning.AI: Large Language Models with Semantic Search 1hr ✅
DeepLearning.AI: Building Applications with Vector Databases ✅
DeepLearning.AI: Knowledge Graphs for RAG ⬜
DeepLearning.AI: Preprocessing Unstructured Data for LLM Applications ⬜
DeepLearning.AI: Embedding Models: From Architecture to Implementation ✅
DeepLearning.AI: Retrieval Optimization - From Tokenization to Vector Quantization ✅
Pinecone: Vector Databases in Production for Busy Engineers ✅
Pinecone: Retrieval Augmented Generation ✅
Pinecone: Faiss: The Missing Manual ✅
Pinecone: Natural Language Processing for Semantic Search 0/13
Youtube: Systematically improving RAG applications ✅
Youtube: Back to Basics for RAG w/ Jo Bergum ✅
Youtube: Beyond the Basics of Retrieval for Augmenting Generation (w/ Ben Clavié) ✅
Youtube: RAG From Scratch 14/14 ✅
Youtube: CMU Advanced NLP Fall 2024 (10): Retrieval and RAG 1h17m ✅
Guidance: Token Healing ⬜
Youtube: What You See Is What You Search: Vision Language Models for PDF Retrieval [Jo Bergum] ✅

Agentic Engineering

Resource Progress
Berkeley: CS294/194-196 Large Language Model Agents 0/14 lectures ⬜
Berkeley: Advanced LLM Agents MOOC 0/12 lectures ⬜
Article: Tool Invocation - Demonstrating the Marvel of GPT's Flexibility ✅
Article: Introducing smolagents, a simple library to build agents ⬜
Article: What Problem Does The Model Context Protocol Solve? ✅
Article: Don’t Build Multi-Agents ✅
Article: Coding Agents 101: The Art of Actually Getting Things Done ⬜
Article: What makes Claude Code so damn good (and how to recreate that magic in your agent)!? ⬜
Anthropic: Building effective agents ✅
Anthropic: Building Effective Agents Cookbook ✅
Anthropic: Writing effective tools for agents — with agents ⬜
OpenAI: Assistants & Agents Build Hour ✅
OpenAI: Function Calling Build Hour ✅
DeepLearning.AI: Agentic AI with Andrew Ng ✅
DeepLearning.AI: Functions, Tools and Agents with LangChain ⬜
DeepLearning.AI: Building Agentic RAG with LlamaIndex ✅
DeepLearning.AI: Multi AI Agent Systems with crewAI ✅
DeepLearning.AI: Building Towards Computer Use with Anthropic ✅
DeepLearning.AI: Pydantic for LLM Workflows ✅
DeepLearning.AI: Practical Multi AI Agents and Advanced Use Cases with crewAI ⬜
DeepLearning.AI: LLMs as Operating Systems: Agent Memory ✅
DeepLearning.AI: Serverless Agentic Workflows with Amazon Bedrock ⬜
DeepLearning.AI: AI Agentic Design Patterns with AutoGen ⬜
DeepLearning.AI: AI Agents in LangGraph ⬜
DeepLearning.AI: Building Your Own Database Agent ⬜
DeepLearning.AI: Function-Calling and Data Extraction with LLMs 59m ✅
DeepLearning.AI: Evaluating AI Agents 2h16m ✅
DeepLearning.AI: Build Apps with Windsurf’s AI Coding Agents 1h10m ✅
DeepLearning.AI: Building AI Browser Agents ⬜
Huggingface: Agents Course Unit 1
Youtube: How to Evaluate Agents: Galileo’s Agentic Evaluations in Action ✅
Youtube: Agent Response | LangSmith Evaluation - Part 24 ✅
Youtube: Single Step | LangSmith Evaluation - Part 25 ✅
Youtube: Agent Trajectory | LangSmith Evaluation - Part 26 ✅
Youtube: Evaluating Agents and Assistants: The AI Conference ✅
Youtube: How to Build, Evaluate, and Iterate on LLM Agents ✅
Youtube: Mem0: Building AI Agents with Scalable Long-Term Memory ⬜
Youtube: How Claude Code Works - Jared Zoneraich, PromptLayer ✅

Context Engineering

Resource Progress
Article: OpenAI Prompt Engineering ⬜
Article: Prompting Fundamentals and How to Apply them Effectively ✅
Article: How I came in first on ARC-AGI-Pub using Sonnet 3.5 with Evolutionary Test-time Compute ✅
Anthropic Courses ⬜
Anthropic: The Claude in Amazon Bedrock Course ⬜
Article: Prompt Engineering(Liliang Weng) ✅
Article: Prompt Engineering 201: Advanced methods and toolkits ✅
Article: Optimizing LLMs for accuracy ✅
Article: Primers • Prompt Engineering ⬜
Article: Anyscale Endpoints: JSON Mode and Function calling Features ⬜
Article: Guided text generation with Large Language Models ⬜
Anthropic: AI Fluency ⬜
Article: Effective context engineering for AI agents ✅
Book: Prompt Engineering for LLMs ⬜
DeepLearning.AI: Reasoning with o1 ✅
OpenAI: Reasoning with o1 Build Hour ✅
DeepLearning.AI: ChatGPT Prompt Engineering for Developers ⬜
Wandb: LLM Engineering: Structured Outputs ⬜
Series: Prompt injection ⬜
Youtube: Prompt Engineering Overview 1hr4m ✅
Youtube: Prompt Engineering Workshop 1h ✅
Youtube: Context Engineering SF - August 20th, 2025 4/4 videos ✅

Quantization

Resource Progress
Article: Quantization Fundamentals with Hugging Face ✅
DeepLearning.AI: Quantization in Depth ⬜
DeepLearning.AI: Introduction to On-Device AI ⬜
Article: A Visual Guide to Quantization ⬜
Article: QLoRA and 4-bit Quantization ⬜
Article: Understanding AI/LLM Quantisation Through Interactive Visualisations ⬜
Youtube: CMU Advanced NLP Fall 2024 (11): Distillation, Quantization, and Pruning ⬜
Article: LLM.int8() and Emergent Features ⬜

Distributed Training

Resource Progress
Youtube: Slaying OOMs with PyTorch FSDP and torchao 49m ✅
Youtube: Distributed Training with PyTorch: complete tutorial with cloud infrastructure and code 1h12m ✅
Youtube: How DDP works || Distributed Data Parallel ✅
Youtube: FSDP Explained ✅
Youtube: Lecture 48: The Ultra Scale Playbook 3h3m 44:24
Youtube: Invited Talk: PyTorch Distributed (DDP, RPC) - By Facebook Research Scientist Shen Li ✅
Youtube: Unit 9 | Techniques for Speeding Up Model Training ✅
Article: A Short Guide to PyTorch DDP ✅
Article: Scaling Deep Learning with PyTorch: Multi-Node and Multi-GPU Training Explained (with Code) ✅
Article: Accelerating PyTorch Model Training ✅
Article: Meet Horovod: Uber’s Open Source Distributed Deep Learning Framework for TensorFlow ✅
Article: Distributed data parallel training in Pytorch ✅
Article: Training on Multiple GPUs ✅
Article: From Single GPU to Clusters: A Practical Journey into Distributed Training with PyTorch and Ray ⬜

Parallel Computing

Resource Progress
Udacity: Intro to Parallel Programming 458 videos 299/458
Book: Programming Massively Parallel Processors: A Hands-on Approach Ch. 2
Youtube: GPU Puzzles: Let's Play ⬜

Inference Optimization

Resource Progress
Article: How to make LLMs go fast ✅
Article: In the Fast Lane! Speculative Decoding - 10x Larger Model, No Extra Cost ⬜
Article: Accelerating Generative AI with PyTorch II: GPT, Fast ⬜
Article: Harmonizing Multi-GPUs: Efficient Scaling of LLM Inference ⬜
Article: Multi-Query Attention is All You Need ⬜
Article: Transformers Inference Optimization Toolset ⬜
DeepLearning.AI: Efficiently Serving LLMs ✅
Article: LLM Inference Series: 3. KV caching explained ⬜
Article: LLM Inference Series: 4. KV caching, a deeper look ⬜
Article: LLM Inference Series: 5. Dissecting model performance ⬜
Article: Transformer Inference Arithmetic ⬜
Article: Optimizing AI Inference at Character.AI ⬜
Article: Optimizing AI Inference at Character.AI (Part Deux) ⬜
Article: llama.cpp guide - Running LLMs locally, on any hardware, from scratch ✅
Article: Domain specific architectures for AI inference ⬜
Youtube: SBTB 2023: Charles Frye, Parallel Processors: Past & Future Connections Between LLMs and OS Kernels ✅
Youtube: Deploying Fine-Tuned Models 2h28m ✅
Article: Compiling ML models to C for fun ⬜
Article: How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklog ⬜
Article: Inside vLLM: Anatomy of a High-Throughput LLM Inference System ⬜
Article: Defeating Nondeterminism in LLM Inference ⬜
Article: Prompt caching: 10x cheaper LLM tokens, but how? ⬜

Evals and Guardrails

Resource Progress
Article: Understanding the 4 Main Approaches to LLM Evaluation (From Scratch) ✅
Article: Your AI Product Needs Evals ✅
Article: Task-Specific LLM Evals that Do & Don't Work ✅
Article: Evaluation & Hallucination Detection for Abstractive Summaries ✅
Article: Aligning LLM as judge with human evaluators ✅
Article: Hard-Earned Lessons from 2 Years of Improving AI Applications ✅
Article: Evaluating Long-Context Question & Answer Systems ⬜
DeepLearning.AI: Automated Testing for LLMOps ✅
DeepLearning.AI: Red Teaming LLM Applications ✅
DeepLearning.AI: Evaluating and Debugging Generative AI Models Using Weights and Biases ⬜
DeepLearning.AI: Quality and Safety for LLM Applications ⬜
OpenAI: Evals Build Hour ✅
Youtube: Instrumenting & Evaluating LLMs 2hr33m ✅
Youtube: LLM Eval For Text2SQL 51m ✅
Youtube: A Deep Dive on LLM Evaluation 49m ✅

Finetuning and Distillation

Resource Progress
Article: Tokenization Gotchas ⬜
Article: Practical Tips for Finetuning LLMs Using LoRA (Low-Rank Adaptation) ⬜
OpenAI: GPT-4o mini Fine-Tuning Build Hour ✅
OpenAI: Distillation Build Hour ✅
Article: How to Generate and Use Synthetic Data for Finetuning ✅
DeepLearning.AI: Finetuning Large Language Models ✅
Youtube: Fine-Tuning with Axolotl 2h10m ✅
Youtube: Creating, Curating, and Cleaning Data for LLMs 54m ✅
Youtube: Best Practices For Fine Tuning Mistral 23m ✅
Youtube: Fine Tuning OpenAI Models - Best Practices ✅
Youtube: When and Why to Fine Tune an LLM 1h56m ✅
Youtube: Napkin Math For Fine Tuning Pt. 1 w/Johno Whitaker ✅
Youtube: Napkin Math For Fine Tuning Pt. 2 w/Johno Whitaker ✅
Youtube: Fine Tuning LLMs for Function Calling w/Pawel Garback 1h32m ✅
Youtube: From Prompt to Model: Fine-tuning when you've already deployed LLMs in prod w/Kyle Corbitt 32m ✅
Youtube: Why Fine Tuning is Dead w/Emmanuel Ameisen 50m ✅
Benchmarking QLoRA+FSDP ⬜

LLM System Design

Resource Progress
Article: What We’ve Learned From A Year of Building with LLMs ⬜
Article: Data Flywheels for LLM Applications ⬜
Article: LLM From the Trenches: 10 Lessons Learned Operationalizing Models at GoDaddy ✅
Article: Emerging UX Patterns for Generative AI Apps & Copilots ✅
Article: The Novice's LLM Training Guide ⬜
Article: Pushing ChatGPT's Structured Data Support To Its Limits ✅
Article: GPTed: using GPT-3 for semantic prose-checking ✅
Article: Don't worry about LLMs ⬜
Article: Things we learned about LLMs in 2024 ⬜
Article: Data acquisition strategies for AI-first start-ups ⬜
Article: All about synthetic data generation ✅
DeepLearning.AI: Building Systems with the ChatGPT API ⬜
DeepLearning.AI: Building Generative AI Applications with Gradio ✅
DeepLearning.AI: Open Source Models with Hugging Face ⬜
LLMOps: Building with LLMs ⬜
LLM Bootcamp - Spring 2023 ✅
Youtube: A Survey of Techniques for Maximizing LLM Performance ✅
Youtube: Building Blocks for LLM Systems & Products: Eugene Yan ✅
Youtube: Building LLM Applications 0/8
Article: Emerging Architectures for LLM Applications ✅
Article: Patterns for Building LLM-based Systems & Products ✅
DeepLearning.AI: LLMOps ⬜
DeepLearning.AI: Serverless LLM apps with Amazon Bedrock ⬜
Youtube: Getting the Most Out of Your LLM Experiments 48m ✅

Technical Skills (Libraries/Frameworks/Tools)

AWS

Resource Progress
Udemy: AWS Certified Developer - Associate 2018 ✅

CSS

Resource Progress
Pluralsight: CSS Positioning ✅
Pluralsight: Introduction to CSS ✅
Pluralsight: CSS: Specificity, the Box Model, and Best Practices ✅
Pluralsight: CSS: Using Flexbox for Layout ✅
Code School: Blasting Off with Bootstrap ✅
Pluralsight: UX Fundamentals ✅
Codecademy: Learn SASS ✅
CSS for Javascript Developers ✅
Book: Refactoring UI ⬜
Youtube: How to Make Your Website Not Ugly: Basic UX for Programmers 48m ⬜

Django

Resource Progress
Article: Django, HTMX and Alpine.js: Modern websites, JavaScript optional ✅

HTML

Resource Progress
Codecademy: Learn HTML ✅
Codecademy: Make a website ✅
Article: Alternative Text ⬜

Langchain

Resource Progress
Pinecone: LangChain AI Handbook 0/11
DeepLearning.AI: LangChain for LLM Application Development ⬜
DeepLearning.AI: LangChain: Chat with Your Data ⬜

JavaScript

Resource Progress
Udacity: ES6 - JavaScript Improved ✅
Udacity: Intro to Javascript ✅
Udacity: Object Oriented JS 1 ✅
Udacity: Object Oriented JS 2 ✅
Udemy: Understanding Typescript ✅
Codecademy: Learn JavaScript ✅
Codecademy: Jquery Track ✅
Pluralsight: Using The Chrome Developer Tools ✅

Matplotlib

Resource Progress
Datacamp: Introduction to Seaborn ✅
Datacamp: Introduction to Matplotlib ✅

MLFlow

Resource Progress
Datacamp: Introduction to MLFlow ✅

Numpy

Resource Progress
Youtube: Numpy Array Broadcasting In Python Explained ✅

Nexxt.JS

Resource Progress
Docs: Start building with Next.js

Pandas

Resource Progress
Datacamp: Pandas Foundations ✅
Datacamp: Pandas Joins for Spreadsheet Users ✅
Datacamp: Manipulating DataFrames with pandas ✅
Datacamp: Merging DataFrames with pandas ✅
Datacamp: Data Manipulation with pandas ✅
Datacamp: Optimizing Python Code with pandas ✅
Datacamp: Streamlined Data Ingestion with pandas ✅
Datacamp: Analyzing Marketing Campaigns with pandas ✅
Datacamp: Analyzing Police Activity with pandas ✅

PyTorch

Resource Progress
Article: PyTorch internals ⬜
Article: Taking PyTorch For Granted ⬜
Datacamp: Introduction to Deep Learning with PyTorch ✅
Datacamp: Intermediate Deep Learning with PyTorch ⬜
Datacamp: Deep Learning for Text with PyTorch ⬜
Datacamp: Deep Learning for Images with PyTorch ⬜
Deeplizard: Neural Network Programming - Deep Learning with PyTorch ✅

ReactJS

Resource Progress
Codecademy: Learn ReactJS: Part I ✅
Codecademy: Learn ReactJS: Part II ✅
NexxtJS: React Foundations ⬜

Spacy

Resource Progress
Datacamp: Advanced NLP with spaCy ✅

Tensorflow & Keras

Resource Progress
Datacamp: Introduction to TensorFlow in Python ✅
Datacamp: Deep Learning in Python ✅
Datacamp: Introduction to Deep Learning with Keras ✅
Datacamp: Advanced Deep Learning with Keras ✅
Deeplizard: Keras - Python Deep Learning Neural Network API ✅
Udacity: Intro to TensorFlow for Deep Learning ✅

VSCode

Resource Progress
VSCode Docs: Python Interactive window ⬜

Miscellaneous

Design

Resource Progress
Course: How to Visualize Value ✅
Article: Create an illustration in Figma design ✅
Series: K-12 Figma Design Basics ✅

Finance

Resource Progress
Coursera: Financial Markets ⬜

Marketing

Resource Progress
Course: Build Once, Sell Twice ✅

Search Engine Optimization (SEO)

Resource Progress
Course: Compound Content ✅

Technical Writing

Resource Progress
Google: Technical Writing Course ⬜
Handbook: Writing Better ⬜

About

A log of things I'm learning

twitter.com/amitness

Topics

python nlp machine-learning deep-learning learning-resources llms generative-ai

Resources

Readme

License

MIT license
Activity

Stars

6.8k stars

Watchers

197 watching

Forks

881 forks
Report repository

Contributors 3

  •  
  •  
  •