Miodrag Cekikj · Towards Data Science

  • RAG Retrieves, It Never Remembers. A vendor-neutral blueprint for applications that accumulate understanding. Includes a…

    49 min read

  • A small experiment in remote SQL execution

    16 min read

Latest

  • Two open problems, exact-arithmetic checking and a proof assistant, over a single weekend.

    30 min read

  • Here’s how to be the Data Scientist who thrives in a world where coding is…

    8 min read

  • How AI has massively changed my day-to-day workflow

    5 min read

  • Enterprise Document Intelligence [Vol.1 #13] – Putting the patterns together, and why this is what…

    32 min read

  • A preprocessing pipeline let my car price model peek at the test set before the…

    13 min read

  • Can a language model do live adversarial level design? Yes, emphasis on the adversarial part

    27 min read

  • Google’s Open Knowledge Format (OKF) is a Markdown+YAML skeleton for sharing knowledge between humans and…

    21 min read

  • Enterprise Document Intelligence [Vol.1 #9ter] – The pipeline from Article 9 calls a model at…

    13 min read

  • Learn how to run OpenClaw bots for increased productivity

    9 min read

Editor’s Picks

  • Image inputs and structured outputs with Gemma 4 and Ollama

    9 min read

  • Not all Python data libraries are created equal!

    6 min read

  • How to diversify a budget without losing the shadow prices that explain the result

    6 min read

  • Three GPUs stacked inside an open computer case, lit by a multicoloured RGB light bar running between the heatsinks

    I replayed the same 27 real production tasks through two local models, one hardware upgrade…

    14 min read

  • Many Transformer explainers start with the finished architecture. We ask why it looks the way…

    30 min read

  • Faster dataframe engines are nice, but they don’t reduce the amount of syntax an analyst…

    10 min read

  • A minimal loop with real API calls, validation, compact outputs, and trace evidence before adding…

    21 min read

  • An open, 2.8-trillion-parameter model shipped with 47 pages of its own recipe. Reading it tells…

    26 min read

  • A primer about Semi-Supervised Learning, the approaches taken with different algorithms and the limitations of…

    9 min read

The Variable Newsletter

  • Authors can now benefit from updated earning tiers and a higher article cap

    2 min read

  • Sorting through the good, bad, and ambiguous aspects of vibe coding

    4 min read

Deep Dives

  • From one gradient to every gradient

    15 min read

  • A reproducible Lagos case study with population data, transport access, and airspace constraints

    52 min read

  • Checking an A/B test until it crosses p < 0.05 can turn a nominal 5…

    12 min read

  • A clear, math-first walkthrough of how VAEs learn to generate new data

    11 min read

  • Learn how Spatial Pyramid Pooling enables CNNs to handle any image size, with a from-scratch…

    19 min read

  • A step-by-step guide to building a data agent and conversational interface that let business users…

    11 min read

Read the original on towardsdatascience.com ↗