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…
At QCon AI NYC 2025, Will Hang from OpenAI unveiled Agent RFT—a cutting-edge reinforcement fine-tuning approach for tool-using agents. By optimizing prompts and tasks before model adjustments, Hang showcased effective strategies to enhance decision-making and efficiency, emphasizing a balanced grading system. The session revealed a future where smarter agents reduce latency and improve outcomes.
Durai Arasan explains the architectural strategies used to scale Chase.com to 67M+ active users. He discusses achieving high resilience through multi-region isolation, slashing latency by 71% via edge computing, and utilizing automated "infrastructure repaving" to eliminate security drift. He shares vital lessons on self-healing observability and building an engineering-first culture.
AWS recently announced the public preview of AWS DevOps Agent, a new "frontier agent" that aims to help organizations react more quickly to production incidents, identify root causes, and proactively strengthen system reliability.
Microsoft has officially launched Visual Studio 2026 (version 18), marking what they call the first ‘AI‑native’ release of its flagship integrated development environment. The general availability rollout follows extensive validation via the Insiders channel and reflects a blend of performance optimisations, deep GitHub Copilot integration, and tooling updates across core languages and workloads.
In this article, authors Srikanth Daggumalli and Arun Lakshmanan discuss next-generation context-aware conversational search using OpenSearch and AI agents powered by Large Language Models (LLMs) and Model Context Protocol (MCP).
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
OpenAI at QCon AI NYC: Fine Tuning the Enterprise
At QCon AI NYC 2025, Will Hang from OpenAI unveiled Agent RFT—a cutting-edge reinforcement fine-tuning approach for tool-using agents. By optimizing prompts and tasks before model adjustments, Hang showcased effective strategies to enhance decision-making and efficiency, emphasizing a balanced grading system. The session revealed a future where smarter agents reduce latency and improve outcomes.
By Andrew HoblitzellPresentation: Scaling Cloud and Distributed Applications: Lessons and Strategies From chase.com, #1 Banking Portal in the US
Durai Arasan explains the architectural strategies used to scale Chase.com to 67M+ active users. He discusses achieving high resilience through multi-region isolation, slashing latency by 71% via edge computing, and utilizing automated "infrastructure repaving" to eliminate security drift. He shares vital lessons on self-healing observability and building an engineering-first culture.
By Durai ArasanAWS Debuts “DevOps Agent” to Automate Incident Response and Improve System Reliability
AWS recently announced the public preview of AWS DevOps Agent, a new "frontier agent" that aims to help organizations react more quickly to production incidents, identify root causes, and proactively strengthen system reliability.
By Craig RisiVisual Studio 2026 Released with AI-Native IDE and Performance Boost
Microsoft has officially launched Visual Studio 2026 (version 18), marking what they call the first ‘AI‑native’ release of its flagship integrated development environment. The general availability rollout follows extensive validation via the Insiders channel and reflects a blend of performance optimisations, deep GitHub Copilot integration, and tooling updates across core languages and workloads.
By Edin KapićArticle: NextGen Search - Where AI Meets OpenSearch Through MCP
In this article, authors Srikanth Daggumalli and Arun Lakshmanan discuss next-generation context-aware conversational search using OpenSearch and AI agents powered by Large Language Models (LLMs) and Model Context Protocol (MCP).
By Srikanth Daggumalli, Arun Lakshmanan