Qwen 刚刚发布了 Qwen3.8-Omni-Flash! 同时还发布了两个配套框架, Qwen-Live-Harness, Qwen-MM-Plugins.…
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
Qwen-Live-Harness? 来看看是啥 Qwen 刚刚发布了 Qwen3.8-Omni-Flash! 同时还发布了两个配套框架, Qwen-Live-Harness, Qwen-MM-Plugins. 给大家整理一下都是啥. 首先Qwen3.8-Omni-Flash, 比上一代的Qwen3.5-omni-flash 平均分提升了25%. 其中最猛的就是Agent能力, 有的分数甚至翻倍了. 然后多人重叠会议语音识别的错误率直接从上一代的88%降低到了3%. 真正的可用了. 除此之外, 原生支持最长 1 小时的完整连续音视频输入, 并且API费用降低了98%. 98%是什么概念? 之前音频输入每百万token是18块, 现在是0.8元! 除此之外, 这次还发布了 Qwen3.8-Omni-Flash-Realtime, 这个是超低延迟版本, 能做到听完问题, 稍加思考后开口的效果(20s音频约981ms). 而 Qwen-Live-Harness 和 Qwen-MM-Plugins 又是啥呢? 首先 Qwen-Live-Harness 搞了个悬浮球, 点击后就可以与模型对话了, 它还能做到环境监控, 比如可以跟它说: 我离开一会, 任务跑完了叫我. 它会把任务塞到任务看板里面, 持续跟进任务状态, 最后播报. 而Qwen-MM-Plugins则是个"赋能"
Posted by karminski-牙医 (39.4k followers) 1 days ago · 56 likes · 8.5k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- TikTok reacts to this: — @_AashishReddy
- Lyria 3.5 from Google DeepMind is now live on fal — @fal
- Tested Jev vs GPT-5.6 for predicting my taste in books. — @venturetwins
- Wife wanted 5-yo involved, so Fable gave me a bunch of reading questions to give him to… — @kevinnbass
- opus 5.2 learned to write poems — @aliceisplaying
- meanwhile grok first try: — @thekitze
- Les premières pièces totalement modélisés par GPT6-Astra — @DFintelligence
- gpt 5.6 terra = gpt 6 astra — @notjazii
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 4.7k X accounts over the last 14 days, 1.3k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.