Codetown ::: a software developer's community
If you're a JUG member, the JavaOne event team wants you to know there's a special discount for you:
"We are offering our JUG’s a special discount for the month of June to
register for JavaOne 2014. The discount will provide an additional $200
savings off the current Early Bird price of $1,650. This gives a total
savings of $600 off the on-site price.
JUG members should use the code DJU4.
Tags:
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.
Created by Michael Levin Dec 18, 2008 at 6:56pm. Last updated by Michael Levin May 4, 2018.
Check out the Codetown Jobs group.
AI is here to stay, and it represents a unique and wonderful opportunity for Java and Spring developers. For most people, “AI engineering” simply means calling an LLM-based service over HTTP. In this article, we’ll examine the new Spring AI 1.0 project and explore how it can be used to integrate AI more effectively.
By Josh LongMistral has released Voxtral, a large language model aimed at speech recognition (ASR) applications that seek to integrate more advanced LLM-based capabilities and go beyond simple transcription. For two variants of the model, Voxtral Mini (3B) and Voxtral Small (24B), Mistral has released the weights under the Apache 2.0 license.
By Sergio De SimoneOpenAI's ChatGPT Agent merges advanced browsing and summarization for seamless data handling. Developers can now generate editable spreadsheets and presentations with simple prompts, integrating outputs directly into productivity tools. With impressive accuracy and connectivity, it enhances workflow efficiency while automating complex tasks, heralding a new era in AI-driven productivity.
By Andrew HoblitzellLeann Chen explains how knowledge graphs enhance LLM-based systems by providing structured data as a ground truth. She demonstrates how this approach combats critical LLM challenges such as hallucinations and the "lost-in-the-middle" phenomenon, especially within RAG applications. She also highlights the struggles of vector-based LLMs with tasks like sorting and filtering.
By Leann ChenAmazon announced the preview of Amazon Bedrock AgentCore, a collection of enterprise-grade services that help developers deploy and operate AI agents at scale across frameworks and foundation models. The platform addresses infrastructure challenges developers face when building production AI agents.
By Vinod Goje
© 2025 Created by Michael Levin.
Powered by