Hermes and Qwen local AI hands-on: usable, with frustrations
What happened
On October 11, The Verge published Antonio G. Di Benedetto's hands-on account of running local AI. He tested Hermes Agent and Qwen 3.8 Flash Next on a Mac Studio with an M5 Ultra, and the experience brought both excitement and choice overload and frustration. The test showed local AI can already handle some everyday tasks, but automation still makes mistakes. The progress on display: local running is practical enough for some work, though finishing some tasks does not mean the automation process won't hit problems.
Written by AI from the coverage · updated 2 hours ago
Coverage
Follow the reports to see the story from different sides.
- The Verge · AILearning to use local AI is exciting, overwhelming, and frustrating
Antonio G. Di Benedetto 在 M5 Ultra Mac Studio 上实测 Hermes Agent 与 Qwen 3.8 Flash Next，本地 AI 已能完成部分日常任务，但自动化仍会出错。
Heat over time
Heat now 9·Comparable peak 10（Oct 11 20:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.