Towards Data Science
May 29
Explaining Lineage in DAX
One of the most important concepts in DAX is lineage. It’s about the information on where something comes from.
How to Solve Issues When You Nest Measures While Overwriting the Same Filter
The article explains how to handle problems that arise when creating a new DAX measure based on an existing one while attempting to overwrite a filter that the nested measure already applies. It discusses the common scenario of reusing measures and the complications that can occur when the same filter is modified in the outer measure. The post provides guidance on resolving these issues to ensure correct calculation results.
Related stories
Towards Data Science
Jul 20
Automatically Assign a Category to Uncategorized Rows in Power Query and DAX
Having categorized data is everything in reporting. Uncategorized data cannot be grouped and aggregated.
Towards Data Science
Aug 6
Loop Engineering for Cross-References: When RAG Answers ‘see Section 7.2’ Instead of the Actual Answer
Enterprise Document Intelligence [Vol. 1 #11] - When the first answer points elsewhere in the document, the pipeline loops back to fetch the linked context The post Loop Engineering for Cross-References: When RAG Answers ‘see Section 7.
Towards Data Science
Aug 22
Why We Fine-Tuned SigLip (And Why That’s Not Always the Right Call)
The article explains how LoRA fine‑tuning addressed an under‑labeling issue in the SigLip model. It outlines that whether this approach is suitable depends on three specific questions. The post provides guidance on evaluating the appropriateness of fine‑tuning for your own use case.
Towards Data Science
4d ago
When All You Have Are Decoders, Every Decision Looks Like Generation
The article titled "When All You Have Are Decoders, Every Decision Looks Like Generation" discusses the misconception that every decision-making process requires a decoder and that generation is not inherently a decision. It highlights that not every decision needs a decoder and clarifies the distinction between generation and decision-making. The piece was originally published on Towards Data Science.
Towards Data Science
May 29
RAG Is Burning Money — I Built a Cost Control Layer to Fix It
Most RAG systems are optimized for answer quality, not cost—and that blind spot gets expensive fast. In this article, I break down a production-ready cost control layer combining semantic caching, query routing, token budgeting, and circuit breaking, achieving an 85% reduction in LLM costs without sacrificing answer quality.
Towards Data Science
Jul 12
RAG vs Fine-Tuning Explained: What They Actually Do and When to Use Each
Two techniques, two different problems, and why the question is not really "which one wins" The post RAG vs Fine-Tuning Explained: What They Actually Do and When to Use Each appeared first on Towards Data Science .
arXiv Machine Learning
Sep 2
Reading the Gate, Not the Interference: Output-Side Interference Measurement Does Not Track Merge Collapse
The paper investigates why task‑arithmetic merging fails by measuring the exact layerwise activation cross‑term of a factorial ledger. It shows that this cross‑term is largely transported and amplified by each block, is regenerated by untouched marginal paths, and varies monotonically with the displacement angle, yet it does not predict merge collapse. The study finds that behavioural performance is decoupled from the cross‑term, and that collapse is driven by marginal displacements rather than the cross‑term, which is only a bystander.
Towards Data Science
Jul 14
How I’m Making Sure My Analytics Career Doesn’t Get Eaten by AI
The analytics career I signed up for five years ago doesn't exist anymore, and honestly, I am fine with that. The post How I’m Making Sure My Analytics Career Doesn’t Get Eaten by AI appeared first on Towards Data Science .
Towards Data Science
Jul 21
I Tried Fine-Tuning a Robot AI Model on Colab. Here Is What Worked
A reproducible 100-step LoRA fine-tuning run for OpenVLA, with dataset checks, Colab setup, training metrics, and W&B evidence. The post I Tried Fine-Tuning a Robot AI Model on Colab.
Towards Data Science
Aug 7
Loop Engineering for Listing Questions: When the Answer Is Every Passage, Not the Top One
Enterprise Document Intelligence [Vol. 1 #12] - The category of question most RAG pipelines silently fail on, and the pipeline shape that handles them The post Loop Engineering for Listing Questions: When the Answer Is Every Passage, Not the Top One appeared first on Towards Data Science .
Simon Willison
Aug 17
Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index
Qwen 3. 8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.