{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Spring Office Hours","title":"S5E26 - dev2Next, Native JSON and a Week of New Models","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/7691894e\"></iframe>","width":"100%","height":180,"duration":3383,"description":"Join Dan Vega and DaShaun Carter for the latest from the Spring ecosystem. We’re back from Dev2Next with a recap. Dan shows off two things he built last week. One is Kiln, a warm new theme for IntelliJ. The other is a set of demos for the JSON API coming to JDK 28. Then we dig into a busy week of model releases. Meta released the weights for Muse Spark Open, NVIDIA fit a 74B model into 24GB, and DeepSeek shipped a faster V4.1 Flash. Local inference is getting real, but RAM and VRAM prices keep climbing. We’ll talk about when running models on your own hardware makes sense, and how to point Spring AI at a model on your own machine. We’ll also answer your questions live.\nShow Notes:\ndev2next Conference\nSpring AI: There and Back Again (demo code)\nArchUnit\nJEP 540: Simple JSON API (Incubator)\nNative JSON demos for JDK 28\nKiln: a warm theme for JetBrains IDEs\nSpring AI Evaluation Testing\nSpring AI Recipes by Craig Walls\nThe show:\nspringofficehours.io - episodes, schedule, community\nSpring Developer on YouTube - join us live every Monday\nDan Vega\nDaShaun Carter\nThe Spring Blog - the news we cover each week","thumbnail_url":"https://img.transistorcdn.com/O8bcAkNs5eCdL9oApddU7M8Z4LjyY4G_kWKMufASgFg/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzQxMDIwLzE2ODIz/ODU0MzItYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}