@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: 42
Followers: 2
How Does a RAG Reranker Really Work?
Published: August 26, 2026 10:30
Enterprise Document Intelligence [Vol.1 #2D] - What data scientists say when asked, what the model actually does under the hood, and why the honest answer changes your architecture decisions in enterprise RAG The post How Does a RAG Reranker Really Work?…
How to Effectively Solve 100+ Tasks with Claude Code
https://towardsdatascience.com/how-to-effectively-solve-100-tasks-with-claude-code/
Published: August 26, 2026 09:00
Work more effectively with your coding agents The post How to Effectively Solve 100+ Tasks with Claude Code appeared first on Towards Data Science.
Why Random Forest Needs to Be This Random
https://towardsdatascience.com/why-random-forest-needs-to-be-this-random/
Published: August 26, 2026 07:30
Bagging hits a wall no amount of trees can break — here's the equation that explains why, and the experiment that proves it The post Why Random Forest Needs to Be This Random appeared first on Towards Data Science.
Is Agentic AI Just Automation?
https://towardsdatascience.com/is-agentic-ai-just-automation/
Published: August 26, 2026 06:00
Why most agents are just flowcharts in disguise, and what to build instead. The post Is Agentic AI Just Automation? appeared first on Towards Data Science.
How to Format Your TDS Draft: A New and Improved Guide
https://towardsdatascience.com/how-to-format-your-tds-draft-a-new-and-improved-guide/
Published: August 26, 2026 01:13
Everything you need to know about creating a draft on our Contributor Portal The post How to Format Your TDS Draft: A New and Improved Guide appeared first on Towards Data Science.
A New Towards Data Science: A Faster Site and a Brand-New Contributor Portal
Published: August 25, 2026 17:25
We're excited to share some big news: We completely rebuilt the TDS website and our contributor portal. Whether you come here to read, to write, or both, here's what you can expect from our new site. The post A New Towards Data Science: A Faster Site and a…
Hallucinations, Watermarks, Removers, and a Squeezed Balloon
https://towardsdatascience.com/hallucinations-watermarks-removers-and-a-squeezed-balloon/
Published: August 25, 2026 13:30
Watermarks act at the model’s moments of doubt, and so do the safety checks that catch AI mistakes The post Hallucinations, Watermarks, Removers, and a Squeezed Balloon appeared first on Towards Data Science.
One Document Type, a Million Files: Structured Extraction into the SQL Table RAG Queries
Published: August 25, 2026 12:00
Enterprise Document Intelligence [Vol.1 #14C] - One hour with two people, six to ten fields, and the two signals that separate a real column from one that will break a filter later The post One Document Type, a Million Files: Structured Extraction into the…
Put Your Own Logic Inside the Codex Agentic Loop
https://towardsdatascience.com/put-your-own-logic-inside-the-codex-agentic-loop/
Published: August 24, 2026 18:00
Understanding Codex hooks The post Put Your Own Logic Inside the Codex Agentic Loop appeared first on Towards Data Science.
10 Positions for Enterprise RAG That Mainstream Tutorials Get Wrong
https://towardsdatascience.com/10-positions-for-enterprise-rag-that-mainstream-tutorials-get-wrong/
Published: August 24, 2026 16:30
Enterprise Document Intelligence [Vol.1 #M3] - The ten positions the series argues from, and the map of every article that argues them The post 10 Positions for Enterprise RAG That Mainstream Tutorials Get Wrong appeared first on Towards Data Science.
Can an LLM Forget the Right Things?
https://towardsdatascience.com/can-an-llm-forget-the-right-things/
Published: August 24, 2026 15:00
Most LLM inference runtimes have no idea a physical deadline exists. This one refuses admission rather than miss a 33ms robot control cycle, evicts KV cache by meaning instead of age, and is written entirely in hand-written CUDA — no cuBLAS, no libtorch.…
Speculative Decoding on CPUs: Nearly 4x Faster Token Generation with DFlash
Published: August 24, 2026 13:30
Speculative decoding can turn underused CPU compute into faster token generation, without changing the model's output. In our vLLM tests, DFlash delivered 3.92x the autoregressive throughput with Qwen3.5-9B on Intel Xeon 6 at concurrency 1. We break down…
AI Agents Don’t Need More Context — They Need Typed Context
https://towardsdatascience.com/ai-agents-dont-need-more-context-they-need-typed-context/
Published: August 24, 2026 12:00
AI agents don’t just have a context problem—they have a context typing problem. When instructions, memory, retrieved evidence, and tool outputs are flattened into one string, their semantic boundaries can disappear. I built a lightweight, zero-dependency…
Survival Analysis and the Cox Proportional Hazards Model: A Beginner-Friendly Guide
https://towardsdatascience.com/a-first-look-at-survival-analysis-and-the-cox-model/
Published: August 23, 2026 17:00
From Kaplan-Meier curves to hazard ratios with runnable Python Code throughout The post Survival Analysis and the Cox Proportional Hazards Model: A Beginner-Friendly Guide appeared first on Towards Data Science.
Parse the Folder, Not Just the PDFs: The Relational Tables RAG Needs on a Case File
Published: August 23, 2026 15:00
Enterprise Document Intelligence [Vol.1 #14D] - The index lists what the case type demands before any folder is opened, and the two questions worth building for are not retrieval questions at all The post Parse the Folder, Not Just the PDFs: The Relational…
Bug Detection Blind Spots in AI Coding Harnesses (GStack and Beyond)
https://towardsdatascience.com/bug-detection-blind-spots-in-ai-coding-harnesses-gstack-and-beyond/
Published: August 23, 2026 13:00
28 debugging experiments reveal that AI struggles less with complexity than with missing information. The post Bug Detection Blind Spots in AI Coding Harnesses (GStack and Beyond) appeared first on Towards Data Science.
Building a Proper Backend for My LangGraph AI Agent
https://towardsdatascience.com/building-a-proper-backend-for-my-langgraph-ai-agent/
Published: August 22, 2026 17:00
Turning a demo agent into something that can keep real booking data The post Building a Proper Backend for My LangGraph AI Agent appeared first on Towards Data Science.
Multi-Document RAG: A Folder of Unrelated PDFs Is One Long Document with a Nested Outline
Published: August 22, 2026 15:00
Enterprise Document Intelligence [Vol.1 #14B] - No shared fields means no index to build. One summary line per file plus each file’s own table of contents, and retrieval routes down two levels The post Multi-Document RAG: A Folder of Unrelated PDFs Is One…
Why We Fine-Tuned SigLip (And Why That’s Not Always the Right Call)
https://towardsdatascience.com/why-we-fine-tuned-siglip-and-why-thats-not-always-the-right-call/
Published: August 22, 2026 13:00
LoRA fine-tuning solved our under-labeling problem. Whether it makes sense for you depends on three questions. The post Why We Fine-Tuned SigLip (And Why That’s Not Always the Right Call) appeared first on Towards Data Science.
Running Codex as a Headless Agent
https://towardsdatascience.com/running-codex-as-a-headless-agent/
Published: August 21, 2026 18:00
Turning Codex from an interactive assistant into a programmable automation component The post Running Codex as a Headless Agent appeared first on Towards Data Science.
Estimating from No Data: Deriving a Continuous Score from Categories
Published: August 21, 2026 17:09
A walkthrough of and the maths behind using low-capacity networks to acquire fine-grained scoring when only categorical labelling is available for training The post Estimating from No Data: Deriving a Continuous Score from Categories appeared first on…
Retrieve One Row from a Table, Not the Whole Table: Row-Level Chunks for RAG
Published: August 21, 2026 16:30
Enterprise Document Intelligence [Vol.1 #7sexies] - The unit of retrieval doesn’t have to be a page or a paragraph. When the corpus carries tables, each body row with its column headers is a chunk in its own right, and it’s often the one row the reader…
The Types of Dimensions in a Star Schema, and How to Use Them
Published: August 21, 2026 15:00
Dimensions are one of the two main object types in dimensional modelling. But what are the different types of dimensions? And how can you use them? The post The Types of Dimensions in a Star Schema, and How to Use Them appeared first on Towards Data…
Bayesian Guardrails for AI Decisions: Measuring Uncertainty Before Automating Decisions
Published: August 21, 2026 13:30
AI systems should not automate a decision simply because they can provide a prediction. A decision system should consider how uncertain the prediction is and defer if a mistake would be costly. The post Bayesian Guardrails for AI Decisions: Measuring…
How Benders Decomposition Works, Part II: Feasibility Cuts
https://towardsdatascience.com/how-benders-decomposition-works-part-ii-feasibility-cuts/
Published: August 21, 2026 12:00
Learning about Farkas' lemma and how it can inform Benders decomposition to learn from infeasibility, applied to the capacitated facility location problem. The post How Benders Decomposition Works, Part II: Feasibility Cuts appeared first on Towards Data…
How to Effectively Align Your Intent with Claude Code
https://towardsdatascience.com/how-to-effectively-align-your-intents-with-claude-code/
Published: August 20, 2026 18:00
Improve your proficiency with Claude Code. The post How to Effectively Align Your Intent with Claude Code appeared first on Towards Data Science.
The LLM Judge That Kept Agreeing With Itself
https://towardsdatascience.com/the-llm-judge-that-kept-agreeing-with-itself/
Published: August 20, 2026 16:30
What a production incident taught me about trusting a model to judge another model's work The post The LLM Judge That Kept Agreeing With Itself appeared first on Towards Data Science.
Three Kinds of RAG Corpus, and What It Costs to Build for the Wrong One
Published: August 20, 2026 15:00
Enterprise Document Intelligence [Vol.1 #14A] - Three questions tell you which shape a document collection has, and each shape wants a different architecture The post Three Kinds of RAG Corpus, and What It Costs to Build for the Wrong One appeared first on…
How to Fine-Tune an LLM: An End-to-End Guide
https://towardsdatascience.com/how-to-fine-tune-an-llm-an-end-to-end-guide/
Published: August 20, 2026 13:30
A hands-on guide to fine-tuning LLMs for the real world The post How to Fine-Tune an LLM: An End-to-End Guide appeared first on Towards Data Science.
Making the Knowledge Layer a Graph You Actually Traverse
https://towardsdatascience.com/making-the-knowledge-layer-a-graph-you-actually-traverse/
Published: August 20, 2026 12:00
Why retrieval quality should be a property of the system, not of the question's wording? Rebuilding knowledge layer with graph traversal on every query, bitemporal edges, and two-threshold entity resolution. The post Making the Knowledge Layer a Graph You…
How to Scale an Integration Pipeline Without Breaking Correctness
https://towardsdatascience.com/scaling-an-integration-pipeline-without-breaking-correctness/
Published: August 19, 2026 18:00
A production account of scaling an enterprise integration pipeline from 500 to 8,000 events per second, and the two correctness guarantees the throughput work was never allowed to trade away. The post How to Scale an Integration Pipeline Without Breaking…
Kimi K3’s 1M Token Context Window vs. RAG: Cost, Latency and Answer Quality
Published: August 19, 2026 16:30
A controlled comparison of a top-5 RAG pipeline and a full 127,000 token prompt on the same 12 questions, same system prompt and same model. Graded blind on correctness, completeness and grounding. The post Kimi K3’s 1M Token Context Window vs. RAG: Cost,…
Understanding Anti-AI Public Opinion
https://towardsdatascience.com/understanding-anti-ai-public-opinion/
Published: August 19, 2026 15:00
People can accept tradeoffs when they see value — but if they don’t, what happens? The post Understanding Anti-AI Public Opinion appeared first on Towards Data Science.
Jigsaw Jeeves: Building a Puzzle Assistant using Computer Vision
https://towardsdatascience.com/jigsaw-jeeves-building-a-puzzle-assistant-using-computer-vision/
Published: August 19, 2026 12:00
Conceptual overview and walkthrough of a solution approach in Python The post Jigsaw Jeeves: Building a Puzzle Assistant using Computer Vision appeared first on Towards Data Science.
From Prototype to Production: The Architecture Behind Secure & Governed AI Agents
Published: August 18, 2026 16:30
Building the Responsible AI, security, and governance layers required for enterprise-ready agents The post From Prototype to Production: The Architecture Behind Secure & Governed AI Agents appeared first on Towards Data Science.
Building Enterprise Agent Systems that People can Trust, Verify and Improve
Published: August 18, 2026 15:00
5 principles that determine whether an agent system succeeds in production, explained through one I built for a $100M+ company. The post Building Enterprise Agent Systems that People can Trust, Verify and Improve appeared first on Towards Data Science.
Graph Engineering Isn’t About More Connections — It’s About Which Ones Get Used
Published: August 18, 2026 13:30
Adding more communication pathways between agents doesn’t necessarily improve multi-agent performance. In a controlled, reproducible experiment across 50 runs, recovery remained remarkably stable from 20% to 100% relationship density. But as the network…
Ten Is Not a Hundred
https://towardsdatascience.com/ten-is-not-a-hundred/
Published: August 18, 2026 12:00
The number that fooled every hallucination detector The post Ten Is Not a Hundred appeared first on Towards Data Science.
Webwright: Why AI Web Agents Should Write Code, Not Click
https://towardsdatascience.com/webwright-why-ai-web-agents-should-write-code-not-click/
Published: August 17, 2026 16:30
For years, web agents have worked one click at a time—and often fallen apart on long tasks. Microsoft Research’s Webwright makes a different bet: give the model a terminal and let it write the program instead. On long-horizon tasks, the same GPT-5.4 model…
Three Generations of Autoscaling — And Why Agentic Traffic Breaks All of Them
Published: August 17, 2026 15:00
How autonomous agents broke two decades of capacity planning — and what to build instead The post Three Generations of Autoscaling — And Why Agentic Traffic Breaks All of Them appeared first on Towards Data Science.
How to Perform Effective Project Management with AI
https://towardsdatascience.com/how-to-perform-effective-project-management-with-ai/
Published: August 17, 2026 13:30
Become a more productive software engineer with LLMs The post How to Perform Effective Project Management with AI appeared first on Towards Data Science.
Loop Engineering for RAG: The Small Loops Inside Each Step, the Big Loops Across the Pipeline
Published: August 17, 2026 12:00
Enterprise Document Intelligence [Vol.1 #13bis] - The four bricks return useful results most of the time. Loop engineering is what the system does the rest of the time: when retrieval misses, when generation fails the schema, when the listing comes back…