好的，我现在需要帮用户总结一篇关于Elloe AI的文章，控制在100字以内。首先，我得通读整篇文章，抓住主要信息。 文章的开头提到Owen Sakawa是Elloe AI的创始人，他想让自己的平台成为AI的“免疫系统”和“杀毒软件”。这说明Elloe AI的主要功能是保护AI模型免受各种问题的影响。 接下来，文章详细介绍了Elloe AI的工作原理。它作为一个API或SDK，位于LLM的输出层之上，负责检查每个响应。检查的内容包括偏见、幻觉、错误、合规问题、虚假信息和不安全输出。这里有几个关键点：检查的范围和层次结构。 Sakawa提到Elloe AI有三个层次或“锚点”：第一个是事实核查，第二个是合规性检查，第三个是审计追踪。这些层次确保了输出的准确性和合规性，并且可以追踪决策过程。 另外，文章指出Elloe AI不依赖于LLM本身，而是使用机器学习等技术，并且有员工参与审核新规定。这表明Elloe AI的方法不仅依赖技术，还有人工监督。 最后，文章提到Elloe AI在TechCrunch Disrupt大会上的表现，作为Top 20决赛选手之一。这可能是一个重要的市场信号，说明该平台得到了认可。 总结一下，我需要将这些要点浓缩到100字以内。重点包括：Elloe AI的功能、其作为API/SDK的角色、三个层次的检查机制、不依赖LLM以及人工审核的存在。 现在开始组织语言： Owen Sakawa创立的Elloe AI旨在成为AI的免疫系统和杀毒软件。它作为API/SDK位于LLM输出层上，通过三个层次检查偏见、错误、合规性等问题，并提供审计追踪。该平台不依赖LLM本身，而是使用机器学习并结合人工审核。 这样大约控制在100字左右，并且涵盖了主要信息。 </think> Owen Sakawa创立的Elloe AI旨在成为AI的免疫系统和杀毒软件。它作为API/SDK位于LLM输出层上，通过三个层次检查偏见、错误、合规性等问题，并提供审计追踪。该平台不依赖LLM本身，而是使用机器学习并结合人工审核。 2025-10-28 19:4:16 Author: techcrunch.com(查看原文) 阅读量:6 收藏
Owen Sakawa, the founder of Elloe AI, wants his platform to be the “immune system for AI” and the “antivirus for any AI agent.”
The idea, Sakawa said in an interview days before the TechCrunch Disrupt conference, where Elloe AI is a Top 20 finalist in the Startup Battlefield competition, is to add a layer to companies’ LLMs that checks for bias, hallucinations, errors, compliance issues, misinformation, and unsafe outputs.
“AI is evolving at a very fast pace, and it’s moving this fast without guard rails, without safety nets, without mechanism to prevent it from ever going off the rails,” Sakawa (pictured above) said.
Elloe AI is an API or an SDK, a module that sits on top of an AI model’s output layer, an “infrastructure on top of your LLM pipeline,” as Sakawa explained. “And it sits there basically fact-checking every single response.”
The startup’s system has its own layers, or “anchors,” as Sakawa put it.
The first anchor fact-checks the LLMs response against verifiable sources. Then, the second anchor checks if the output violates any regulations, such as the U.S. health privacy law HIPAA, the European far-reaching data protection and privacy law GDPR, or if it exposes some Personal Private Information (PII). The last anchor is an audit trail that shows how all the previous decisions were made and allows regulators or anyone auditing the system “to analyze the train of thought for that model from where it made the decision the source of that decision, the confidence score of all those decisions,” according to Sakawa.
To be clear, Sakawa said Elloe AI is not built on an LLM, because in his opinion, having LLMs checking other LLMs is just putting a “Band-Aid into another wound.” Elloe AI’s system does use AI techniques, though, such as machine learning. And there are humans in the loop: Elloe AI’s employees, who keep up with new regulations on data protection and user protection, Sakawa said.
Techcrunch event
San Francisco | October 27-29, 2025
If you want to learn more about Elloe AI — while also checking out dozens of other companies, hearing their pitches, and listening to guest speakers on four different stages — join us at Disrupt, October 27 to 29, in San Francisco. Learn more here.
Lorenzo Franceschi-Bicchierai is a Senior Writer at TechCrunch, where he covers hacking, cybersecurity, surveillance, and privacy.
You can contact or verify outreach from Lorenzo by emailing [email protected], via encrypted message at +1 917 257 1382 on Signal, and @lorenzofb on Keybase/Telegram.
如有侵权请联系:admin#unsafe.sh