Ivan Karabadzhak’s Post

Claude Add-In for Excel Apparently Claude for Excel is powerful because it uses python execution layer behind the scenes. Instead of forcing everything in a formula it translates everything into a python script. This gives it alot of flexibility to handle messier datasets than formulas and is definately more reliable for complex logic. Its like having a python engine for your spreadsheet, since its release about a month ago I was hooked and have not made another excel formula since. Give it a try its extremely powerful #Anthropic #Claude #Excel #AI #Automation

Starting a Python interpreter takes ~1 microsecond with Monty. A sandbox call takes ~1 second. That's 6 orders of magnitude. And no external service, no cgroups, no VM. Samuel Colvin explains why he built a Python interpreter in Rust from scratch for AI agents on his PyAI talk. Link in comments.

The bottleneck in AI-assisted coding isn't the model or your prompts. When an agent can't see your notebook state, it guesses. You're relaying error messages and stuck in the (endless) loop at every step. With marimo-pair, coding agents get a live view of your notebook. Variables, errors, UI elements - if you can interact with it, the agent can too. PS: you're also not paying per token to analyze your own CSV files. https://lnkd.in/gcBjKijm #python #AI #datascience #openSource #mlops

‼️FREE SERIES ALERT Part 2: Framework to Implement Any ML Algorithm From Scratch (Python) | Full Beginner to Advanced AI This series is designed for beginners in AI/ML who want to move beyond "black-box" libraries and truly understand the software architecture expected in tech interviews. If you're preparing for ML roles and want to truly understand how algorithms work under the hood, this series is for you. https://lnkd.in/g6tQ9Y79

512: Agentic loops are more than instructions. They're like installable packages for Python or Spark, capable of processing code and expounding patterns. Think of publishing to PDF using specific CSS and tools – it's a skill that deserves more credit. #AI #AgenticAI #MachineLearning #TechInnovation #FutureofAI

Built an MCP server from scratch to understand how the protocol actually works step by step. It is a practical tutorial to understand how MCP works under the hood instead of treating it like magic. Repo -> https://lnkd.in/gqGe7W6R #Python #AI #MCP #SoftwareEngineering #Backend

OpenAI just acquired the Python tooling team. Astral (Ruff, uv, ty) → now part of Codex. The numbers that got them acquired: - Hundreds of millions of downloads/month - Ruff became the default Python linter - uv replaced pip for most devs The tools stay open source. But they're now building at "the frontier of AI and software." When the best dev tools company joins the best AI company, something's shifting. The IDE wars are over. The agent wars just started. #Python #OpenAI #Codex #DevTools #AI

Sorting lists of dictionaries or objects in Python often means writing small, repetitive lambda functions. There's a cleaner, faster way to grab specific items for sorting or processing. This little trick makes your data operations much more elegant and performant ✨. Do you use `itemgetter` or stick with `lambda` for sorting? Share your preferred method below! #Python #MachineLearning #AI #CodingTips #PythonTips

Ever feel your Python loops are a bit clunky? You often calculate a value. Then you immediately check it in the next line. This trick lets you assign and check a variable *right inside* your condition. It makes data processing cleaner and more direct for AI/ML tasks. 💡 Do you use the walrus operator? Or what's your favorite Python trick for cleaner loops? #Python #AI #MachineLearning #CodingTips #Tech