@towardsdatascience.com.source.rss----7f60cf5620c9---4@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Your home for data science. A Medium publication sharing concepts, ideas and codes. - Medium
Site URL: towardsdatascience.com?source=rss----7f60cf5620c9---4
Feed URL: towardsdatascience.com/feed
Posts: 47
Followers: 2
GraphRAG: A Practitioner's Guide to 6 Advanced Architectural Patterns
https://towardsdatascience.com/graphrag-a-practitioners-guide-to-6-advanced-architectural-patterns/
Published: September 20, 2026 15:00
Beyond basic graph retrieval: six production-oriented architectures for combining semantic search, knowledge graphs, and LLM reasoning. The post GraphRAG: A Practitioner's Guide to 6 Advanced Architectural Patterns appeared first on Towards Data Science.
CBAM Paper Walkthrough: The Double-Attention Mechanism
https://towardsdatascience.com/cbam-paper-walkthrough-the-double-attention-mechanism/
Published: September 20, 2026 13:00
Understanding and implementing CBAM (Convolutional Block Attention Module) from scratch with PyTorch The post CBAM Paper Walkthrough: The Double-Attention Mechanism appeared first on Towards Data Science.
One Vendor, Four Spellings: How Deterministic Stages Beat Similarity Scores
Published: September 19, 2026 15:00
Deduplicating a 10,000-row supplier list in Python, where the hard part is deciding what a similarity score of 91 means The post One Vendor, Four Spellings: How Deterministic Stages Beat Similarity Scores appeared first on Towards Data Science.
AI Made Me 5x Faster. It Also Made Me 5x Worse at My Job.
https://towardsdatascience.com/ai-made-me-5x-faster-it-also-made-me-5x-worse-at-my-job/
Published: September 19, 2026 13:00
One near miss, four months of running agents, and the question almost nobody is asking: what are you supposed to do while the AI writes the code? The post AI Made Me 5x Faster. It Also Made Me 5x Worse at My Job. appeared first on Towards Data Science.
Coding Agents Keep Shipping Silent Failures — Here Is How to Catch Them
Published: September 18, 2026 15:30
How to verify your app aligns with your intent without ever reading a line of generated code. The post Coding Agents Keep Shipping Silent Failures — Here Is How to Catch Them appeared first on Towards Data Science.
We Pinned Our Model Version to Stay Safe. The Provider Deprecated It Anyway.
Published: September 18, 2026 14:00
The recurring cost of production AI is not inference. It is re-qualification: the eval reruns, prompt retuning, and regression testing you owe every time a model changes under you. Here is what that tax actually covers, and how to budget for it before it…
Starting a Career in Data Science in the Age of AI
https://towardsdatascience.com/starting-a-career-in-data-science-in-the-age-of-ai/
Published: September 18, 2026 12:30
How do you set yourself up for a career that will stand the test of time when things are changing so fast? The post Starting a Career in Data Science in the Age of AI appeared first on Towards Data Science.
Multi-Agent Coding Isn’t Enough — Agents Need a Commitment Layer
https://towardsdatascience.com/multi-agent-coding-isnt-enough-agents-need-a-commitment-layer/
Published: September 18, 2026 11:00
Multi-agent coding systems don't necessarily fail because agents can't communicate. They can fail because important commitments made in conversation have nowhere to live afterward. The post Multi-Agent Coding Isn’t Enough — Agents Need a Commitment Layer…
Building a Data Lakehouse with DuckDB and DuckLake
https://towardsdatascience.com/building-a-data-lakehouse-with-duckdb-and-ducklake/
Published: September 17, 2026 15:30
Starting with a local Parquet file, then joining it to data stored in the cloud The post Building a Data Lakehouse with DuckDB and DuckLake appeared first on Towards Data Science.
How I Built a Multi-Agent System for Interrupted Time Series Analysis (ITSA)
Published: September 17, 2026 14:00
What it takes to turn counterfactual analysis into an AI product The post How I Built a Multi-Agent System for Interrupted Time Series Analysis (ITSA) appeared first on Towards Data Science.
Why You Think Like a Bayesian but Were Taught Like a Frequentist
https://towardsdatascience.com/why-you-think-like-a-bayesian-but-were-taught-like-a-frequentist/
Published: September 17, 2026 12:30
From a chocolate bar with no price tag to a marketing mix model in PyMC, and the 200-year-old integral that stood in between. The post Why You Think Like a Bayesian but Were Taught Like a Frequentist appeared first on Towards Data Science.
When Does Graph RAG Actually Add Value? A Hands-On Experiment
https://towardsdatascience.com/when-does-graph-rag-actually-add-value-a-hands-on-experiment/
Published: September 17, 2026 11:00
I built four AI retrieval architectures on a laptop and benchmarked them against the same set of documents and questions. Here’s what the results taught me about the trade-offs between plain RAG, graph RAG, and simply putting everything into a frontier…
How to Make Linear Regression Survive Outliers
https://towardsdatascience.com/how-to-make-linear-regression-survive-outliers/
Published: September 16, 2026 15:30
Robust Estimation Series: comparing classical and modern robust estimators through theory, code, and experiments The post How to Make Linear Regression Survive Outliers appeared first on Towards Data Science.
Silent Broadcasting Can Ruin Your Model
https://towardsdatascience.com/silent-broadcasting-can-ruin-your-model/
Published: September 16, 2026 14:00
PyTorch and TensorFlow tensor broadcasting: how silent shape errors cause difficult-to-debug machine learning bugs The post Silent Broadcasting Can Ruin Your Model appeared first on Towards Data Science.
The KV Cache Tax: Why Inference Servers Run Out of Memory Before Compute
Published: September 16, 2026 12:30
A VRAM budget formula for LLM serving, and three optimization strategies mapped to the traffic patterns that trigger the OOM. The post The KV Cache Tax: Why Inference Servers Run Out of Memory Before Compute appeared first on Towards Data Science.
The N Squared Pizza Problem
https://towardsdatascience.com/the-n-squared-pizza-problem/
Published: September 16, 2026 11:00
What ordering and not eating a large pizza tells us about ML memory management The post The N Squared Pizza Problem appeared first on Towards Data Science.
Reparameterization Tricks: Variance Reduction by Smarter Gradients
https://towardsdatascience.com/reparameterization-tricks-variance-reduction-by-smarter-gradients/
Published: September 15, 2026 15:30
How moving randomness outside the computation graph turns noisy gradient estimators into low-variance, differentiable ones The post Reparameterization Tricks: Variance Reduction by Smarter Gradients appeared first on Towards Data Science.
How to Build Consistent Designs with Claude Code
https://towardsdatascience.com/how-to-build-consistent-designs-with-claude-code/
Published: September 15, 2026 14:00
Keep your apps looking professional with Claude Code design skills The post How to Build Consistent Designs with Claude Code appeared first on Towards Data Science.
Seizing the Moment: The Hidden Silhouette of Data
https://towardsdatascience.com/seizing-the-moment-the-hidden-silhouette-of-data/
Published: September 15, 2026 12:30
How statistical moments connect the mean, the variance, and higher powers of a distribution The post Seizing the Moment: The Hidden Silhouette of Data appeared first on Towards Data Science.
How Many Labeled Examples Does a Text Classifier Actually Need? I Measured It.
Published: September 15, 2026 11:00
Before reaching for an LLM API on every classification problem, it's worth knowing what a decades-old baseline can already do with the labeled data you have — and exactly how much more data buys you. The post How Many Labeled Examples Does a Text…
Your Model’s MSE Is Lying to You
https://towardsdatascience.com/your-models-mse-is-lying-to-you/
Published: September 14, 2026 19:30
First in a series on probabilistic forecasting for physical signals. Next: what happens when you roll the forecast forward more than one step. The post Your Model’s MSE Is Lying to You appeared first on Towards Data Science.
When to Use One Model and When to Use a Team of Agents
https://towardsdatascience.com/when-to-use-one-model-and-when-to-use-a-team-of-agents/
Published: September 14, 2026 17:52
When Codex is the right shape for the problem, when Claude Code is, and how I split 5 specialist agents between them on dense AI capacity work. The post When to Use One Model and When to Use a Team of Agents appeared first on Towards Data Science.
Graph Engineering for AI Agents: From Prompts and Loops to Workflows
https://towardsdatascience.com/graph-engineering-for-ai-agents-from-prompts-and-loops-to-workflows/
Published: September 14, 2026 12:30
A viral debate over loops versus graphs points to a bigger shift in how we build AI systems. Here’s what graph engineering actually means, how it differs from prompt, context, and loop engineering, and why it matters. The post Graph Engineering for AI…
From Static to Dynamic Skills: A Different Model for Agent Knowledge
https://towardsdatascience.com/from-static-to-dynamic-skills-a-different-model-for-agent-knowledge/
Published: September 14, 2026 11:00
Why the skill-inflation panic is aimed at the wrong thing, and what it costs to make agent knowledge a build artifact instead of a file. The post From Static to Dynamic Skills: A Different Model for Agent Knowledge appeared first on Towards Data Science.
Your Model Isn't Done Until Someone Else Can Call It
https://towardsdatascience.com/your-model-isnt-done-until-someone-else-can-call-it/
Published: September 13, 2026 15:00
Building a FastAPI endpoint for churn prediction, and everything that broke between "it runs" and "it's live The post Your Model Isn't Done Until Someone Else Can Call It appeared first on Towards Data Science.
Your AI Adoption Lift Is a Selection Effect
https://towardsdatascience.com/your-ai-adoption-lift-is-a-selection-effect/
Published: September 13, 2026 12:00
A practitioner's guide to estimating what an opt-in AI feature actually did, when nobody randomized it. The post Your AI Adoption Lift Is a Selection Effect appeared first on Towards Data Science.
One Capital Letter Was Silently Breaking My AI Support Bot, and It Wasn't in the New Model
Published: September 12, 2026 14:00
A real Weave project that regression-tests three OpenAI models against the exact reply format your app depends on. The post One Capital Letter Was Silently Breaking My AI Support Bot, and It Wasn't in the New Model appeared first on Towards Data Science.
Stop Managing Alarms: An Incident-First Blueprint for Telecom AIOps
https://towardsdatascience.com/stop-managing-alarms-an-incident-first-blueprint-for-telecom-aiops/
Published: September 12, 2026 11:00
What large operators can teach us about turning alert fatigue into faster, safer service assurance The post Stop Managing Alarms: An Incident-First Blueprint for Telecom AIOps appeared first on Towards Data Science.
Coding Agents Don't Need Longer History — They Need Intent Continuity
https://towardsdatascience.com/coding-agents-dont-need-longer-history-they-need-intent-continuity/
Published: September 11, 2026 15:30
I built a system that automatically discovers, verifies, and applies relevant requirements from earlier interactions without asking the user where they came from. The post Coding Agents Don't Need Longer History — They Need Intent Continuity appeared first…
Software Design in the Age of AI
https://towardsdatascience.com/software-design-in-the-age-of-ai/
Published: September 11, 2026 14:00
Why AI coding makes software design more important The post Software Design in the Age of AI appeared first on Towards Data Science.
The 95% Illusion: Why Your Confidence Interval Isn't What You Think It Is
Published: September 11, 2026 12:30
Frequentist confidence intervals and Bayesian credible intervals answer different questions, and confusing them can distort product decisions The post The 95% Illusion: Why Your Confidence Interval Isn't What You Think It Is appeared first on Towards Data…
Demystifying Anthropic's J-Space: A Mathematical Primer
https://towardsdatascience.com/demystifying-anthropics-j-space-a-mathematical-primer/
Published: September 11, 2026 11:00
Clarifying the math behind Anthropic’s representation workspace The post Demystifying Anthropic's J-Space: A Mathematical Primer appeared first on Towards Data Science.
How to 5x Your Communication Effectiveness with Claude Code
https://towardsdatascience.com/how-to-5x-your-communication-effectiveness-with-claude-code/
Published: September 10, 2026 15:30
Better understand the intent of your coding agents The post How to 5x Your Communication Effectiveness with Claude Code appeared first on Towards Data Science.
What SHAP Can't Explain About Agentic AI Fraud
https://towardsdatascience.com/what-shap-cant-explain-about-agentic-ai-fraud/
Published: September 10, 2026 14:00
Why autonomous agents expose a new explainability problem in fraud detection The post What SHAP Can't Explain About Agentic AI Fraud appeared first on Towards Data Science.
Optimizing LLM Inference Costs in Multi-Agent Systems with Adaptive Model Routing
Published: September 10, 2026 12:30
Moving from static model assignment to intelligent, task-level LLM selection. The post Optimizing LLM Inference Costs in Multi-Agent Systems with Adaptive Model Routing appeared first on Towards Data Science.
Who Questions What Works: When Should We Retest Our Assumptions?
https://towardsdatascience.com/who-questions-what-works-when-should-we-retest-our-assumptions/
Published: September 10, 2026 11:00
A model is only as reliable as the assumptions behind it The post Who Questions What Works: When Should We Retest Our Assumptions? appeared first on Towards Data Science.
Getting started with dbt
https://towardsdatascience.com/getting-started-with-dbt/
Published: September 9, 2026 15:30
A practical guide to building, testing, and documenting SQL transformations The post Getting started with dbt appeared first on Towards Data Science.
The Symmetry That Breaks Neural Network Averaging
https://towardsdatascience.com/the-symmetry-that-breaks-neural-network-averaging/
Published: September 9, 2026 14:00
Understanding permutation symmetry in deep learning, and what it means for weight averaging and model merging The post The Symmetry That Breaks Neural Network Averaging appeared first on Towards Data Science.
When One Process Becomes Too Much: Splitting a Pipeline into MCP Services
Published: September 9, 2026 12:30
How we split a tightly coupled Python pipeline into independently deployable services The post When One Process Becomes Too Much: Splitting a Pipeline into MCP Services appeared first on Towards Data Science.
10 Statistical Traps We Often Overlook
https://towardsdatascience.com/10-statistical-traps-we-often-overlook/
Published: September 9, 2026 11:00
Statistical thinking beyond formulas The post 10 Statistical Traps We Often Overlook appeared first on Towards Data Science.
How to Maximize GPT-6 Astra
https://towardsdatascience.com/how-to-maximize-gpt-6-astra/
Published: September 8, 2026 18:00
My first impressions of OpenAI's new frontier model The post How to Maximize GPT-6 Astra appeared first on Towards Data Science.
The Model Validation Playbook for GenAI: Lessons from Banking
https://towardsdatascience.com/the-model-validation-playbook-for-genai-lessons-from-banking/
Published: September 8, 2026 17:34
How model validation standards are changing for LLM-based systems: what breaks, what carries over, and how to test output quality The post The Model Validation Playbook for GenAI: Lessons from Banking appeared first on Towards Data Science.
A Beginner’s Guide to World Models
https://towardsdatascience.com/a-beginners-guide-to-world-models/
Published: September 8, 2026 17:27
Learn how to simulate reality with Python The post A Beginner’s Guide to World Models appeared first on Towards Data Science.
Introducing ShipAI
https://towardsdatascience.com/introducing-shipai/
Published: September 8, 2026 13:41
Towards Data Science launches a video showcase for real-world AI work The post Introducing ShipAI appeared first on Towards Data Science.
Context Windows Don’t Know What’s Still True — I Built a Validity Layer That Does
Published: September 8, 2026 11:00
A context window can be technically complete and still describe a world that no longer exists. I built a deterministic benchmark to measure the cost of acting on stale context. The post Context Windows Don’t Know What’s Still True — I Built a Validity…
I Vibe-Coded an App in Just Two Hours (And Regretted It the Next Day)
https://towardsdatascience.com/i-vibe-coded-an-app-in-just-two-hours-and-regretted-it-the-next-day/
Published: September 7, 2026 14:00
I saved my day with a mere $52 bill. But you don't have to repeat my mistake. The post I Vibe-Coded an App in Just Two Hours (And Regretted It the Next Day) appeared first on Towards Data Science.
Why Most Multi-Agent Systems Fail Even When Evaluation Passes
https://towardsdatascience.com/why-most-multi-agent-systems-fail-even-when-evaluation-passes/
Published: September 7, 2026 12:00
How to catch a payload that looks correct but isn't, using a watchdog pattern with working Python. The post Why Most Multi-Agent Systems Fail Even When Evaluation Passes appeared first on Towards Data Science.