{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"AI News Today | Julian Goldie Podcast","title":"Hermes Agent V0.18 Just Changed AI Agents Forever!","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/530a82f6\"></iframe>","width":"100%","height":180,"duration":null,"description":"Hermes Agent v0.18 “Judgment” Update: Mixture of Agents, /goal Loops, /learn Skills + Proof-of-Work\nThis episode breaks down the Hermes Agent v0.18 “Judgment” release and demonstrates key additions, especially the new Mixture of Agents system that fuses outputs from multiple models (e.g., Claude Opus 4.8 and GPT 5.5) to improve quality, with results shown on Goldie Bench and described as a one-shot workflow that can take 10–15 minutes per run. It covers improved /goal “goal mode” with a judge-driven loop that verifies work against a definition of done, plus proof-of-work for coding by running project checks instead of accepting “done” claims. The script also highlights /learn for turning guides or repos into reusable skills, /journey for a timeline of what Hermes has learned, background fan-out for asynchronous sub-agents, three ways to update Hermes, and how these features are organized inside the creator’s Agent OS and AI Profit Boardroom system.\n00:00 Hermes V0.18 Overview\n00:25 Mixture Of Agents\n01:34 Benchmarks And Tradeoffs\n02:58 Goal Mode Looping\n04:15 Why Use Agent OS\n05:01 Learn And Journey\n06:30 Updating And Fan Out\n07:50 Delegating Sub Agents\n09:15 Proof Of Work\n10:00 Boardroom Systems Tour\n11:06 Community And Training\n12:21 Final Call To Action","thumbnail_url":"https://img.transistorcdn.com/Tp0JSUlyiAe2ran44b13cjk4ImQYS1QEMKCAa9Q7go0/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9lNTYz/NGQxMTU2ZTM1MzU5/MDNiYjcwZjJmYTY5/ODJmOS5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}