|
Aug 9, 2026
|
How Prompt Evaluation Pipelines Work
|
7 min
|
|
Aug 9, 2026
|
Cascade or Native? What the Voice AI Stack Actually Looks Like in 2026
|
30 min
|
|
Aug 8, 2026
|
LLM API Pricing Compared: Claude, GPT, Gemini, and the Chinese Challengers (August 2026)
|
15 min
|
|
Aug 8, 2026
|
Waiting, and Not Waiting
|
10 min
|
|
Aug 6, 2026
|
Stop Parsing Prose
|
6 min
|
|
Aug 5, 2026
|
The One Thing Always in the Room
|
4 min
|
|
Aug 5, 2026
|
Can You Invert a Recursive Function?
|
3 min
|
|
Aug 3, 2026
|
Built for Problems It Has Never Seen
|
3 min
|
|
Aug 3, 2026
|
Your LLM Has No Memory. Everything Else Is Engineering.
|
10 min
|
|
Aug 3, 2026
|
From Formants to Foundation Models
|
15 min
|
|
Aug 2, 2026
|
LLM Agents from First Principles
|
10 min
|
|
Jul 31, 2026
|
Explainability Is a Localization Problem
|
33 min
|
|
Jul 30, 2026
|
Nvidia Bought the Team Behind the Library I Contribute To
|
3 min
|
|
Jul 28, 2026
|
The Professor Who Let Us Break R First
|
3 min
|
|
Jul 28, 2026
|
Swarms in Worktrees: How Claude Code Agents Work in Parallel
|
10 min
|
|
Jul 27, 2026
|
‘It Works on My Machine’: The Ladder of Numerical Dependencies
|
14 min
|
|
Jul 26, 2026
|
Why the Bayesian Bootstrap?
|
77 min
|
|
Jul 24, 2026
|
The Poor Person’s Bayesian
|
73 min
|
|
Jul 24, 2026
|
Skills Ate Commands: What Changed in Claude Code
|
18 min
|
|
Jul 24, 2026
|
Lost in Translation: How Math Tribes Speak Different Languages (And Why Epidemiologists Hate MSE)
|
18 min
|
|
Jul 23, 2026
|
From First Principles to Interior Point Methods: The Physics of Constrained Convex Optimization
|
32 min
|
|
Jul 23, 2026
|
LangGraph vs LlamaIndex: One Agent, Two Architectures
|
21 min
|
|
Jul 23, 2026
|
Training vs. Calibrating Epidemiological Models: A First-Principles Guide
|
44 min
|
|
Jul 23, 2026
|
Maximum-Margin Classification from First Principles: SVMs as Convex Optimization
|
35 min
|
|
Jul 23, 2026
|
What TDA Actually Builds: A Filtered Simplicial Complex, Not a Fancy Graph
|
29 min
|
|
Jul 23, 2026
|
Uses and Abuses of Topological Data Analysis: A Pragmatic Guide
|
28 min
|
|
Jul 22, 2026
|
Two Ways to Expand the Space: Persistent Homology and Kernel SVMs on the Same Toy Dataset
|
14 min
|
|
Jul 22, 2026
|
Topological Data Analysis: Finding Clusters, Loops, and Voids Across Scales
|
14 min
|
|
Jan 8, 2026
|
Thoughts on Unsupervised Learning
|
4 min
|
|
Apr 9, 2025
|
AI Engineer vs ML Engineer vs Data Scientist: Roles, Tools, and Code Quality
|
6 min
|
![]()
|
Apr 9, 2025
|
Cursor AI
|
2 min
|
![]()
|
Apr 9, 2025
|
Model Evaluation Metrics
|
8 min
|
![]()
|
Apr 8, 2025
|
Classifying PDF Documents with RAG and LLMs
|
11 min
|
![]()
|
Apr 7, 2025
|
Apple Silicon, Docker, and ML Environments
|
2 min
|
![]()
|
Apr 6, 2025
|
Hugging Face Hub Python SDK
|
5 min
|
![]()
|
Apr 6, 2025
|
Accelerating Transformers with Hugging Face Optimum
|
7 min
|
![]()
|
Apr 6, 2025
|
Transformers Library for NLP
|
9 min
|
![]()
|
Apr 5, 2025
|
Introduction to Diffusers by Hugging Face
|
9 min
|
![]()
|
Apr 4, 2025
|
Hugging Face Datasets
|
7 min
|
![]()
|
Apr 4, 2025
|
Efficient Few-Shot Learning with SetFit from Hugging Face
|
8 min
|
![]()
|
Apr 2, 2025
|
Why Snowflake is a Game-Changer for Data Warehousing
|
4 min
|
![]()
|
Apr 1, 2025
|
AI Programming Writing Blog Posts
|
1 min
|
![]()
|
Apr 1, 2025
|
RAG Again
|
3 min
|
![]()
|
Mar 31, 2025
|
An Overview of Apache Airflow
|
5 min
|
![]()
|
Mar 31, 2025
|
Model Monitoring
|
5 min
|
![]()
|
Mar 30, 2025
|
Soft Prompts vs. Hard Prompts
|
7 min
|
![]()
|
Mar 27, 2025
|
Exploring Vector Databases: Weaviate vs Pinecone
|
4 min
|
![]()
|
Mar 27, 2025
|
Why PySpark?
|
3 min
|
![]()
|
Mar 26, 2025
|
Building Complex LLM Workflows with LangGraph
|
5 min
|
![]()
|
Mar 22, 2025
|
dbt
|
3 min
|
![]()
|
Mar 21, 2025
|
Embeddings: Text, Image, and Voice
|
3 min
|
![]()
|
Mar 20, 2025
|
Hugging Face Tokenizers Library
|
6 min
|
![]()
|
Mar 16, 2025
|
Apache Flink: Understanding Stream Processing and Comparisons with NiFi and Kafka
|
4 min
|
![]()
|
Mar 16, 2025
|
LangChain: Introduction
|
7 min
|
![]()
|
Mar 16, 2025
|
Parameter-Efficient Fine-Tuning with Hugging Face’s peft Library
|
6 min
|
![]()
|
Mar 12, 2025
|
Evaluating NLP Models with the Hugging Face evaluate Library
|
8 min
|
![]()
|
Mar 12, 2025
|
NiFi
|
8 min
|
![]()
|
Mar 11, 2025
|
Databricks: Some Notes
|
3 min
|
![]()
|
Mar 3, 2025
|
Docker for Machine Learning: A Deep Dive into Layers and Deployment
|
4 min
|
![]()
|
Mar 2, 2025
|
Kafka and AWS Streaming Services
|
3 min
|
![]()
|
Feb 25, 2025
|
Data Types: Structured, Unstructured, and Semi-Structured Data
|
8 min
|
![]()
|
Feb 21, 2025
|
Quarto Workshop
|
3 min
|
![]()
|
Feb 20, 2025
|
Feature Importance After Clustering
|
2 min
|
![]()
|
Feb 17, 2025
|
What is Retrieval-Augmented Generation (RAG)
|
3 min
|
![]()
|
Feb 9, 2025
|
First Job in Industry
|
1 min
|
![]()
|
Feb 7, 2025
|
Python Books I Recommend
|
2 min
|
![]()
|
Feb 6, 2025
|
Reinforcement Learning
|
12 min
|
![]()
|
Feb 4, 2025
|
Python Method Naming Conventions: Best Practices for Class Design
|
4 min
|
![]()
|
Feb 3, 2025
|
Building a Simple Vector Database in Python
|
5 min
|
![]()
|
Feb 2, 2025
|
Why Use Conda for Scientific Computing?
|
3 min
|
![]()
|
Jan 31, 2025
|
Understanding Attention: From Theory to Implementation
|
4 min
|
![]()
|
Jan 27, 2025
|
Hyperparameter Tuning in Clustering Algorithms: A Complete Guide
|
5 min
|
![]()
|
Jan 21, 2025
|
Markdown: What’s in the name?
|
1 min
|
![]()
|
Sep 21, 2024
|
Minimal Data Inspection Before Splitting The Dataset
|
5 min
|
![]()
|
Sep 21, 2024
|
sklearn vs R model APIs
|
14 min
|
![]()
|
Sep 20, 2024
|
Train Dev Test Data Splits
|
10 min
|
![]()
|
Sep 19, 2024
|
Model Speciation
|
7 min
|
![]()
|
Apr 22, 2024
|
Git Repository Search
|
5 min
|
![]()
|
Apr 11, 2024
|
Sparsity with PyTorch Tensors
|
9 min
|
![]()
|
Apr 9, 2024
|
Streamlining Development with Make, CI/CD, and GitHub Actions
|
4 min
|
![]()
|
Mar 3, 2024
|
Developing Pytorch Geometric on M1 Apple Silicon
|
7 min
|
![]()
|
Feb 9, 2024
|
Post With Code and Plot
|
1 min
|
![]()
|
Feb 6, 2024
|
Welcome To Synthetic Musings
|
1 min
|
