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…
DoorDash has launched a multimodal machine learning system that aligns product images, text, and user queries in a shared embedding space. Trained on 32 million labeled query-product pairs using contrastive learning, the system improves semantic search, product ranking, and advertising relevance. Embeddings also support other machine learning tasks across the marketplace.
Stefan Dirnstorfer discusses the shift from DOM-based testing to visual UI agents. He explains why LLMs often fail at precision tasks - like spotting one-pixel shifts or broken road networks - and shares how advanced image registration and "Chain-of-Thought" vision processing are essential for reliable QA. Learn why combining generative AI with classical algorithms is the future of automation.
Celebrating its 23rd year, Devnexus 2026 was held from March 4-6, 2026 at the Georgia World Congress Center in Atlanta, Georgia. The event featured speakers from the Java community who delivered workshops and talks under tracks such as: AI Generative; AI in Practice; Core Java; Java Frameworks; and Security and Developer Tools.
Andres Almiray, a serial open-source contributor and the creator of JReleaser, discusses the project's state, noting that the tool is usable across any ecosystem, not just Java. He also touches on the Common House Foundation's mission.
This article introduces practical methods for evaluating AI agents operating in real-world environments. It explains how to combine benchmarks, automated evaluation pipelines, and human review to measure reliability, task success, and multi-step agent behavior. The article also discusses the challenges of evaluating systems that plan, use tools, and operate across multiple interaction turns.
Reply Deleted
This reply has been deleted. Return to the discussion.
Welcome to
Codetown
Sign Up
or Sign In
Or sign in with:
Happy 10th year, JCertif!
Notes
Welcome to Codetown!
Created by Michael Levin Dec 18, 2008 at 6:56pm. Last updated by Michael Levin May 4, 2018.
Looking for Jobs or Staff?
InfoQ Reading List
DoorDash Builds DashCLIP to Align Images, Text, and Queries for Semantic Search Using 32M Labels
DoorDash has launched a multimodal machine learning system that aligns product images, text, and user queries in a shared embedding space. Trained on 32 million labeled query-product pairs using contrastive learning, the system improves semantic search, product ranking, and advertising relevance. Embeddings also support other machine learning tasks across the marketplace.
By Leela KumiliPresentation: Image Processing for Automated Tests
Stefan Dirnstorfer discusses the shift from DOM-based testing to visual UI agents. He explains why LLMs often fail at precision tasks - like spotting one-pixel shifts or broken road networks - and shares how advanced image registration and "Chain-of-Thought" vision processing are essential for reliable QA. Learn why combining generative AI with classical algorithms is the future of automation.
By Stefan DirnstorferDevnexus 2026: Focus on AI with Core Java, Java Frameworks, Security and Career Mentoring
Celebrating its 23rd year, Devnexus 2026 was held from March 4-6, 2026 at the Georgia World Congress Center in Atlanta, Georgia. The event featured speakers from the Java community who delivered workshops and talks under tracks such as: AI Generative; AI in Practice; Core Java; Java Frameworks; and Security and Developer Tools.
By Michael RedlichPodcast: Andres Almiray on How to Release Any Software to Any OS with JReleaser
Andres Almiray, a serial open-source contributor and the creator of JReleaser, discusses the project's state, noting that the tool is usable across any ecosystem, not just Java. He also touches on the Common House Foundation's mission.
By Andres AlmirayArticle: Evaluating AI Agents in Practice: Benchmarks, Frameworks, and Lessons Learned
This article introduces practical methods for evaluating AI agents operating in real-world environments. It explains how to combine benchmarks, automated evaluation pipelines, and human review to measure reliability, task success, and multi-step agent behavior. The article also discusses the challenges of evaluating systems that plan, use tools, and operate across multiple interaction turns.
By Amit Kumar Padhy