AI-generated recap of Devoxx Belgium 2024 opening keynote : Genesis
summary
Demos show a plugin called devox Genie that runs AI models locally for code generation and code review, already ported to VS Code and demoed live; a Java-native LLM stack called Jalama runs models locally, supports LangChain4J function-calling and even shards a model across multiple machines; a local-inference effort around llama 3 Java emphasizes performance tweaks plus grvm for faster runtimes; claims focus on privacy, latency, and practical integrations with Java tooling and VS Code.
AI-written summary · about
chapters (13)
- 0:00The future of Java and AI
- 0:34Devoxx Genie plugin
- 1:21Local AI and open source
- 2:30JLama vector database
- 3:35Integrating AI with Java
- 4:48Embracing technological change
- 5:43AI in real-world challenges
- 6:22Oracle's vision for Java AI
- 7:11Optimizing local inference
- 8:17GraalVM performance boost
- 9:24Call to action for developers
- 10:08Conclusion and next steps
- 11:36Sequence ending
related talks
46mThe Era of AAP: Ai Augmented Programming using Modern Java
14mInterview of Stephan Janssen
38mThe Era of AAP: Ai Augmented Programming using only Java
46mAI-powered Java Developers
46mThe Era of AAP: Ai Augmented Programming using only Java
33mThe Future of Developer Experience with GenAI: Driving Engineering Excellence
01h 01mUnlocking AI's Potential: Smarter Coding in Apache NetBeans IDE
53mUnlocking AI's Potential: Smarter Coding in Apache NetBeans IDE
