Sophia NLU 家庭助手 – 设备端运行、低计算需求、无需互联网、语音助手
Sophia NLU 是一款基于 Rust 的设备端低计算量自然语言理解引擎，充当对话代理。它提供了大型语言模型（LLM）的流畅性，但只需 160MB 的内存，不需要 GPU。它可以处理无限设备、多重意图、模糊性、上下文意识，延迟仅为毫秒，不连接互联网，也不会向外发送数据。
<p>刚刚发布的 v1.2 版本升级，详细信息请访问：https://nlu.tech/r/ha_v10200
<p>此次升级带来了许多改进：
<p>* 当不确定您指的是哪个实体时，Sophia 现在会请求澄清。
* 状态持久性。例如，如果您询问厨房里有多少盏灯亮着，您可以在下一条消息中说“把它们关掉”，Sophia 会记住您指的是哪些灯。
* 帮助改善 Sophia！当 Sophia 未能正确理解一条消息时，只需告诉 Sophia 上一条消息是错误的。该信息将被记录，您可以不时通过网页界面的日志菜单手动上传所有待处理的记录以供审核和修复。
* 还有更多...
<p>立即获取 Sophia 的免费试用，几分钟内即可设置： https://nlu.tech/ha/
<p>免费试用结束后，您可以支付少量费用，或者仅需推荐一位付费客户即可获得终身许可证，完全免费。基本上，相当于买一送一的优惠。
<p>内置助手非常严格，只允许单一意图，并要求设备的友好名称。LLM 需要 GPU，容易出现幻觉并给出概率性错误。而且没有人希望将他们的消息通过网络发送给大型科技公司。Sophia 解决了这一痛点，兼顾质量和隐私。
<p>手工打造，而非随意编码。这实际上是经过 2.5 年的研发，经过多个月的升级，现已推出 HA 版本。我对这项技术有着宏大的抱负，因此我会全力以赴，确保您获得最佳的软件，并且它能完全按照您的需求工作。如果有任何问题，请随时告知，我们会解决。
<p>我的邮箱始终开放，如果您需要我，可以联系我：matt@cicero.sh。自从突然失明以来，我经历了非常艰难的几年，如果您能帮我分享一下这条信息，我将不胜感激。
查看原文
Sophia NLU is an on device, low compute, Rust based natural language understanding engine that acts as a conversation agent. It offers the fluidity of a LLM without the compute, requiring only 160MB of RAM, no GPU. Handles unlimited devices, multiple intents, ambiguity, contextual awareness, millisecond latency, doesn't connect to the internet, and never calls home.<p>Upgrade to v1.2 just released with details at: https://nlu.tech/r/ha_v10200<p>This upgrade comes with many improvements:<p>* Sophia will now ask for clarification if it's uncertain which entity you meant.
* State persistence. For example, if you ask how many lights are on in the kitchen, you can now say "turn them off for me" in the next message and Sophia will remember which lights you mean.
* Help improve Sophia! When Sophia doesn't correctly understand a message, simply tell Sophia the last message was wrong. It will be logged, and once in a while, manually upload all pending through the Log menu of the web interface for review and repair.
* And more...<p>Grab a free trial of Sophia, and be setup within minutes at: https://nlu.tech/ha/<p>After the free trial, you can either pay a small fee or simply refer a single paying customer and get your lifetime license absolutely free. Essentially, a 2 for 1 deal.<p>The built-in Assist is very rigid as it only allows for single intents, and requires the friendly names of devices. LLMs require a GPU, hallucinate and give probabilistic mismatches. And nobody wants to send their messages over the wire to big tech. Sophia solves this pain point with quality and privacy.<p>Hand crafted, not vibe coded. This is actually 2.5 years of R&D with many months and upgrades for the HA edition now. I have huge ambitions for this tech, so am 100% here to ensure you get the best software possible and it works exactly as you need. If there's any issues at all, just simply let them be know, and they will be resolved.<p>My inbox is always open, if you need me, I'm at matt@cicero.sh. I've had a very rough handful of years since going suddenly blind, so if you could do me a favor and share this around it would be greatly appreciated.