@kdnuggets

Mining insights in data science, machine learning, analytics, and AI • Edited by @mattmayo13 • KD stands for "knowledge discovery"

 San Juan, PR
kdnuggets.com/
Joined February 2009
  • Tweets86.3K
  • Following354
  • Followers219K
32.4KMedia
🤖 AI agents are getting smarter. But can enterprises trust them with real workflows? Building reliable AI agents requires more than powerful models. It also takes trusted data, governance, and the right infrastructure. Join Google Cloud's upcoming online event to explore how Agentic Data Cloud supports the next generation of enterprise AI. 📅 November 5 | 10 AM CET (EMEA) 🔗 Save your spot: cloudonair.withgoogle.com/ev… #AIAgents #GoogleCloud #EnterpriseAI
1
248
I loaded a large JSON file in Python and watched memory jump from 43 MB to 808 MB. Here’s what happened and how streaming changed everything. f.mtr.cool/9v64jih2wb

How to Process Large JSON Files in Python With ijson - KDnuggets

I loaded a large JSON file in Python and watched memory jump from 43 MB to 808 MB. Here’s what happened and how streaming changed everything.

kdnuggets.com
508
Google's Harness² lets AI agents improve their prompts, tools, memory, and scripts through two recursive loops without touching model weights. Learn more, including how to run the free demo yourself. f.mtr.cool/wb8u56k339

Google Open-Sources Harness²: Self-Improving AI Agents Without Retraining

Google Research has open-sourced Harness² (Harness2), a framework that lets AI agents improve themselves without retraining the underlying model. Instead of touching model weights, Harness² rewrites...

kdnuggets.com
1
2
846
Build standardized custom NER pipelines in a few simple steps, powered by the reasoning capabilities of LLMs. f.mtr.cool/rcueu57tq6

Named Entity Recognition Using Scikit-LLM - KDnuggets

Build standardized custom NER pipelines in a few simple steps, powered by the reasoning capabilities of LLMs.

kdnuggets.com
1
4
1,402
Explore five popular AI agent skill collections that help coding agents plan, test, debug, review, and build better software. f.mtr.cool/k6yb851wz5

5 Best GitHub Repositories for AI Agent Skills - KDnuggets

Explore five popular AI agent skill collections that help coding agents plan, test, debug, review, and build better software.

kdnuggets.com
1,047
Don't miss Snowflake Expedition 2026 – a global virtual experience designed to turn data engineering, analytics, and AI into high-impact, business-ready workflows. Whether you’re a builder or a leader, Expedition offers tailored learning paths so you can go heavy on execution and focus on real business outcomes! What to expect: ⚡ AI Luminary fireside chat with Satya Nadella, Chairman and CEO, Microsoft and Sridhar Ramaswamy, CEO, Snowflake ⚡ Technical hands-on labs, live demos, and minimal slides. ⚡ A first look at Snowflake CoCo, AI agent-building tools, and enterprise AI workflows. ⚡ Real-world strategies from industry-leading organizations using the Snowflake AI Data Cloud. 📅 Dates: November 3–6, 2026 💻 Location: Free Virtual Event  🔗 Register now for free: snowflake.com/en/expedition/…
2
2
1,085
🚀 Ready to turn agentic AI into real business impact? Join Google Cloud for Trusted Agents, Real Outcomes, an online event exploring how Agentic Data Cloud can help organizations build trusted AI workflows and scale AI initiatives. Discover what it takes to move from AI experimentation to practical business outcomes. 📅 November 5 | 10 AM CET (EMEA) 🔗 Register now: cloudonair.withgoogle.com/ev… #GoogleCloud #AgenticAI #DataEngineering
1
992
A structured four-phase roadmap for building the technical fluency, evaluation skills, and governance literacy needed to succeed as an AI product manager in 2026. f.mtr.cool/ynp3nv0udk

The Roadmap to Becoming an AI Product Manager in 2026 - KDnuggets

A structured four-phase roadmap for building the technical fluency, evaluation skills, and governance literacy needed to succeed as an AI product manager in 2026.

kdnuggets.com
4
1,201
Five self-hosted Docker containers replace the public utility sites where developer data quietly leaks. Learn which ones handle JWT decoding, data transformation, file conversion, API testing, and diagram rendering locally. f.mtr.cool/ucs0ycewv5

5 Docker Containers for Devs - KDnuggets

Five self-hosted Docker containers replace the public utility sites where developer data quietly leaks. Learn which ones handle JWT decoding, data transformation, file conversion, API testing, and...

kdnuggets.com
4
1,421
Claude Haiku 5.5 cuts list prices by 90% and adds adaptive thinking and a 1M token context window. Learn what broke from Haiku 4.5, and build classification, extraction, and sub-agent workflows in Python using the new API. f.mtr.cool/rx0dwyavza

Claude Haiku 5.5: What's New and How to Use It for Fast, Cheap AI Workflows

Anthropic released Claude Haiku 5.5 on October 7, 2026, and calls it its cheapest, fastest, and most capable small model. The API model ID is claude-haiku-5-5, and prompts up to 100,000 tokens cost...

kdnuggets.com
1
2
1,711
Choosing the right framework for your large language model application comes down to one question: what are you actually optimizing for? f.mtr.cool/2diftvo27j

LangChain vs. LlamaIndex vs. Building From Scratch: Here's What I Suggest - KDnuggets

Choosing the right framework for your large language model application comes down to one question: what are you actually optimizing for?

kdnuggets.com
1
2
1,388
AI makes writing code cheap. Verifying it is still your job. f.mtr.cool/oam879b6s8

7 Checks to Run Before Trusting AI-Generated Code - KDnuggets

AI makes writing code cheap. Verifying it is still your job.

kdnuggets.com
1,796
Earn your MS in Data Science in one year bit.ly/4yuIUhH
2
7
6,079
From static retrieval pipelines to autonomous reasoning engines: a complete breakdown of how these two architectures work, where each falls short, and how to choose the right one for your use case. f.mtr.cool/xfktrryzi2

Agentic RAG vs. Naive RAG: When Your Retrieval System Should Think for Itself - KDnuggets

From static retrieval pipelines to autonomous reasoning engines: a complete breakdown of how these two architectures work, where each falls short, and how to choose the right one for your use case.

kdnuggets.com
1
1,916
World models could be the next big shift in AI. Learn more right now. f.mtr.cool/afnwyhm5xr

5 Best Resources to Learn About World Models in 2026 - KDnuggets

World models could be the next big shift in AI. Learn more right now.

kdnuggets.com
1
1,684
Abacus AI Honest Review: Key Criticisms, Facts & What Users Should Know kdnuggets.com/2026/10/abacus…
3
1,625
This review highlights the main critiques of Abacus AI, its price, user reviews, reliability of workflows, and real-life use cases to assist you in evaluating its advantages and disadvantages. f.mtr.cool/40j5jmedr5

Abacus AI Review: Criticisms, Facts & What Users Should Know

Explore Abacus AI’s features, pricing, credit system, user criticisms, workflow reliability, and real-world use cases to decide whether it fits your needs.

kdnuggets.com
1,211
OGX is an open-source agentic API server for building OpenAI-compatible AI applications, using any model and any infrastructure. f.mtr.cool/ko8rls0if7

Building AI Applications with Open-Source Agentic API Server OGX

OGX is plainly described as: an open-source agentic API server for building AI applications, OpenAI-compatible, any model, any infrastructure. It is the rebrand of Meta's Llama Stack, with the name...

kdnuggets.com
1
3
1,593
Find open-source alternatives to OpenAI API, Midjourney, Claude Code, Notion, Wispr Flow, Grammarly, and NotebookLM that you can run locally or self-host for more privacy, control, and lower cost. f.mtr.cool/mco8wthv7j

7 Open-Source AI Tools That Can Replace Paid Subscriptions - KDnuggets

Find open-source alternatives to OpenAI API, Midjourney, Claude Code, Notion, Wispr Flow, Grammarly, and NotebookLM that you can run locally or self-host for more privacy, control, and lower cost.

kdnuggets.com
1
2
1,856
Leveraging Scikit-LLM for one of the simplest yet most practical text classification tasks utilized in the modern AI landscape: few-shot classification. f.mtr.cool/nfaz5ygxoq

Few-Shot Text Classification with Scikit-LLM - KDnuggets

Leveraging Scikit-LLM for one of the simplest yet most practical text classification tasks utilized in the modern AI landscape: few-shot classification.

kdnuggets.com
1
1
5
2,399
Load more