July 2016 Blog Posts (3)

Going Pro in Data Science

When you're learning data science, you usually practice with nice, clean, pre-packaged data sets and tidy case studies that lead you step-by-step from data collection to cool insights.

But when real life hits, many data scientists have to work with missing or sketchy information extracted from (multiple) sources in the organization. Data science that works is a messy, trial-and-error process of creating and testing hypotheses, gathering evidence, and drawing conclusions.

Going Pro in… Continue

Added by Michael Levin on July 31, 2016 at 2:17pm — No Comments

Call for proposals: The O'Reilly Design Conference

O'Reilly has just opened the call for proposals for their second Design Conference, coming to San Francisco March 19–22, 2017. Got something to share with the design community? Think it over and submit your idea by September 7, 2016.
http://www.oreilly.com/pub/cpc/24650

Added by Michael Levin on July 28, 2016 at 7:55pm — No Comments

Enter for a chance to win!

O'Reilly technology conferences help you change your business—and change the world—by bringing you face-to-face with the knowledge of innovators and practitioners. Discover the right conference for you below and enter to win a Platinum pass!

"The O'Reilly conferences are the gold standard for drawing together a critical mass of thought leaders." —Steve Gillmor, CRN

Link: http://www.oreilly.com/pub/cpc/24305

Added by Michael Levin on July 26, 2016 at 12:39pm — No Comments

Monthly Archives

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

Happy 10th year, JCertif!

Notes

Welcome to Codetown!

Codetown is a social network. It's got blogs, forums, groups, personal pages and more! You might think of Codetown as a funky camper van with lots of compartments for your stuff and a great multimedia system, too! Best of all, Codetown has room for all of your friends.

When you create a profile for yourself you get a personal page automatically. That's where you can be creative and do your own thing. People who want to get to know you will click on your name or picture and…
Continue

Created by Michael Levin Dec 18, 2008 at 6:56pm. Last updated by Michael Levin May 4, 2018.

Looking for Jobs or Staff?

Check out the Codetown Jobs group.

 

Enjoy the site? Support Codetown with your donation.



InfoQ Reading List

From Black Box to Blueprint: Thoughtworks Uses Generative AI to Extract Legacy System Functionality

Thoughtworks consultants successfully harnessed generative AI to decode legacy systems lacking source code. Using Gemini 2.5 Pro, they accelerated reverse engineering, creating validated "blueprints" of functionality in just two weeks. The pilot showcased AI's potential to drastically reduce time and risk in modernizing opaque systems while balancing speed with validation.

By Matt Foster

Introducing the MCP Registry

The Model Context Protocol (MCP) ecosystem is enhancing AI development with a public registry for server discovery and a secure gateway for agent interactions. This initiative, featuring the recently launched MCP Registry and the Linux Foundation's Agentgateway project, streamlines the management of AI tools, fostering collaboration and security for engineering teams.

By Andrew Hoblitzell

Presentation: Chatting with Your Knowledge Graph

Jonathan Lowe explains how to connect an LLM directly to a structured graph database using a rapid prototype. He demonstrates how to use sentence embeddings and semantic search to allow natural language queries to retrieve and analyze structured data. This approach enables a local LLM to answer complex questions by leveraging the relationships within a knowledge graph.

By Jonathan Lowe

Pinterest Unifies Engineering Tools with New Pinconsole Platform

Pinterest has introduced PinConsole, a unified internal developer platform (IDP) that centralizes engineering workflows. Built to address fragmented tools for deployment, monitoring, and service management, PinConsole provides a consistent layer that lets engineers focus on business logic instead of infrastructure complexity.

By Leela Kumili

How LinkedIn Built Enterprise Multi-Agent AI on Existing Messaging Infrastructure

LinkedIn extended its generative AI application platform to support multi-agent systems by repurposing its existing messaging infrastructure as an orchestration layer. This allowed the company to scale AI agents without building new coordination technology from scratch and achieve global availability while supporting complex multi-step workflows through agent coordination.

By Eran Stiller

© 2025   Created by Michael Levin.   Powered by

Badges  |  Report an Issue  |  Terms of Service