Production Monitoring & Automations of LLM with LangSmith 🦜👇🏼
LangChain released a crash course for LangSmith, their DevOps platform for deploying LLM applications into production. The course covers topics such as:
✅ LLM applications monitoring
✅ Setting automation
✅ Performance monitoring
Andrej Karpathy just released a new repo with an implementation of training LLM with pure C/Cude with a few lines of code 🚀. This repo, according to Andrej Karpathy, is still WIP, and the first working example is of GPT-2 (or the grand-daddy of LLMS 😅) 👇🏼
The R Workflow by Prof. Frank E Harrell Jr is a new book (WIP) that focuses on reproducible data analysis and reporting with R. That includes the following topics:
✅ Data processing
✅ Descriptive analysis
✅ Data visualization
✅ Reporting
The Linear Algebra for Data Science course by Shaina Race Bennett provides a light and visual introduction to linear algebra ❤️. The course focuses on the core linear operations and their data science applications:
✅ Matrix operations
✅ Least squares
✅ Covariance
✅ Linear regression
✅ Eigenvalues and Eigenvectors
✅ PCA
The Data Science for Beginner course by Microsoft provides, as the name implies, an introduction to data science. This ten-week course focuses on both theory and tools, such as:
✅ Data structures
✅ Statistics and probability
✅ Python
✅ Data wrangler
✅ Data visualization
You dream it, and we build it!
FREE shipping on the #Linux system you've always dreamed of. Plus, you can upgrade your component options for less on all models.
The Neural Networks from Scratch in #Python 🐍 course by Harrison Kinsley introduces neural networks by coding them from scratch. The course is based on Harrison's book (along with Daniel Kukiela), and it covers the following topics:
✅ Core linear algebra and math operators
✅ Neural network architecture
✅ Different loss functions
✅ Optimization and derivatives
Heute endet unsere Konferenz zu #MachineLearning. Wir danken allen Teilnehmenden!
Es gab spannende Beiträge, u.a. von Susanne Dandl von der Ludwig-Maximilians-Universität München zum Thema interpretierbares #MaschinellesLernen oder Wesley Yung zu #DataScience bei Statistics Canada.
A few days ago, I posted about the Convex Optimization course by Prof. Stephen Boyd from Stanford University. Following this post, multiple people recommended checking the course book - Convex Optimization by Prof. Stephen Boyd and Prof. Lieven Vandenberghe.
Everyone, drop what you are doing - SPURIOUS CORRELATION now has a companion site, SPURIOUS SCHOLAR - that WRITES AN ACADEMIC PAPER based on the spurious correlation! Because "if p < 0.05, why not publish?" 😂
Ready to explore the nexus of finance and R programming? May 18 at UIC is where your journey begins. The R Finance Conference is your one-stop event for cutting-edge financial insights and methodologies, wrapped in a day of expert talks, hands-on workshops, and invaluable networking.
Don’t miss this chance to enhance your finance skills and connect with industry leaders.
(1/2) Setting A Dockerized 🐳 Python 🐍 Environment — The Elegant Way
A few weeks ago, I created a short tutorial about setting up a dockerized 🐳 Python 🐍 environment via the CLI, or the hard way. The second tutorial on this topic provides a more elegant and robust approach for setting up a Python dockerized development environment with VScode and the Dev Containers extension 🚀.
DuckDB released a new R package - duckplyr, which enables running dplyr functions using the DuckDB engine on the backend ❤️. The package, on the backend, translates and maps the dplyr code into DuckDB. This will enable dplyr users to work with large datasets with higher performance.
The terrible human toll in Gaza has many causes.
A chilling investigation by +972 highlights efficiency:
An engineer: “When a 3-year-old girl is killed in a home in Gaza, it’s because someone in the army decided it wasn’t a big deal for her to be killed.”
An AI outputs "100 targets a day". Like a factory with murder delivery:
"According to the investigation, another reason for the large number of targets, and the extensive harm to civilian life in Gaza, is the widespread use of a system called “Habsora” (“The Gospel”), which is largely built on artificial intelligence and can “generate” targets almost automatically at a rate that far exceeds what was previously possible. This AI system, as described by a former intelligence officer, essentially facilitates a “mass assassination factory.”"
"The third is “power targets,” which includes high-rises and residential towers in the heart of cities, and public buildings such as universities, banks, and government offices."
“The #protocol was that even if you don’t know for sure that the machine is right, you know that statistically it’s fine. So you go for it,” said a source who used #Lavender.
“It has proven itself,” said B., the senior officer. “There’s something about the statistical approach that sets you to a certain norm and standard. There has been an illogical amount of [bombings] in this operation. This is unparalleled, in my memory. And I have much more trust in a statistical mechanism than a soldier who lost a friend two days ago. Everyone there, including me, lost people on October 7. The machine did it coldly. And that made it easier.”
Another intelligence source said: “In war, there is no time to incriminate every target. So you’re willing to take the margin of error of using artificial intelligence, risking collateral damage and civilians dying, and risking attacking by mistake, and to live with it.”