<p>The AI revolution isn&#39;t replacing Java developers. No, it&#39;s forcing us to think harder.</p><p>Welcome to another episode of the Foojay Podcast! Today, we&#39;re talking about AI and Java, how it&#39;s changing the way we work, what we need to watch out for, and why understanding what&#39;s really happening matters more than ever.</p><p>I recorded interviews at Devoxx and JFall and spoke with people who build and use this technology every day.</p><p>Marianne Hoornenborg opened my eyes to something important: every time an AI generates a token, there&#39;s a massive amount of computation happening behind the scenes.</p><p>Viktor Gamov and Baruch Sadogursky did something really cool: they tested six different AI coding tools live on stage with the same task. The results were all over the place! But they found that the tools with access to good documentation performed much better.</p><p>Stephen Chin showed me how graph databases can make AI responses more reliable by providing a solid source of truth rather than relying on vector search.</p><p>Mario Fusco works on LangChain4J, a leading Java framework for AI. He explained that breaking down large tasks into smaller ones and using specialized agents can help reduce errors—hallucinations, as they&#39;re called.</p><p>Jeroen Benckhuijsen and Martijn Dashorst shared their experiences working with enterprise Java. Even as frameworks are becoming lighter and we&#39;re running everything in containers, there are still complex problems that require real developer expertise.</p><p>Maarten Mulders reminds us that AI is a tool, not a replacement—especially when you&#39;re solving problems no one has tackled before. You still need to know what you&#39;re doing.</p><p>And finally, Simon Maple from Tessel discussed moving beyond vibe coding towards a more reliable, production-ready approach, using specifications to guide AI tools.</p><p>00:00 Introduction of topics and guests</p><p>02:12 Marianne Hoornenborg </p><ul><li><a href="https://www.linkedin.com/in/mhoornenborg/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/mhoornenborg/</a></li><li>The Simple Math behind AI </li><li>The cost of tokens when using LLMs</li></ul><p>06:54 Viktor Gamov and Baruch Sadogursky </p><ul><li><a href="https://www.linkedin.com/in/vikgamov/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/vikgamov/</a> </li><li><a href="https://www.linkedin.com/in/jbaruch/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/jbaruch/</a> </li><li>Robocoders, about the many agentic tools that can be used for vibe coding </li><li><a href="https://context7.com/" target="_blank" rel="noopener noreferer">https://context7.com/</a></li></ul><p>16:24 Stephen Chin </p><ul><li><a href="https://www.linkedin.com/in/steveonjava/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/steveonjava/</a> </li><li>Graph versus relational databases </li><li>Explaining MCP and Agents</li></ul><p>23:09 Mario Fusco </p><ul><li><a href="https://www.linkedin.com/in/mario-fusco-3467213/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/mario-fusco-3467213/</a> </li><li>AI and LangChain4j in Quarkus </li><li>Coding tools with AI</li></ul><p>35:43 Jeroen Benckhuijsen </p><ul><li><a href="https://www.linkedin.com/in/jeroenbenckhuijsen/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/jeroenbenckhuijsen/</a> </li><li>Java in business, Evolutions in Java </li><li>Making use of containers and Kubernetes </li><li>Learning from the community</li></ul><p>41:44 Martijn Dashorst </p><ul><li><a href="https://www.linkedin.com/in/dashorst/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/dashorst/</a> </li><li>Investigating an OOM-killer in Kubernetes with the help of AI</li></ul><p>49:37 Maarten Mulders </p><ul><li><a href="https://www.linkedin.com/in/mthmulders/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/mthmulders/</a></li><li>How AI may impact our jobs </li><li>How to improve your Maven builds </li></ul><p>56:13 Simon Maple </p><ul><li><a href="https://www.linkedin.com/in/simonmaple/" target="_blank" rel="noopener noreferer">https://www.linkedin.com/in/simonmaple/</a> </li><li>AI developer tool Tessl </li><li>Spec-driven vibe coding </li><li>Secure AI development</li></ul><p>01:02:12 Conclusion</p><p><br></p>