在当今的 世界, 人工智能聊天机器人（例如 ChatGPT 和 Claude）可以执行许多功能,，例如撰写工作电子邮件和规划旅行行程。这些聊天机器人是围绕大型视觉语言模型 (VLMs): AI 构建的系统，该模型在海量数据集上进行训练，其中包括书籍, 网站, 代码, 和图像。
In today的 world, artificial intelligence chatbots such as ChatGPT and Claude can perform many functions, such as composing work emails and planning travel itineraries. These chatbots are systems built around large vision-language models (VLMs): AI trained on a massive dataset that includes books, websites, code, and images.
然后，人工智能算法根据大量人类生成的反馈进行改进，以遵循指令并避免有害或不需要的输出,，并使用该"知识"根据用户的输入生成文本或图像。尽管聊天机器人有明显的局限性,，但它们对于各种任务, 都非常有帮助，包括在一些传统上需要专业技能, 的领域，例如计算机编程。
The AI algorithms are then refined on massive amounts of human-generated feedback to follow instructions and avoid harmful or unwanted output, and use that "knowledge" to produce text or images based on input from a user. Although chatbots have clear limitations, they can be very helpful for a wide range of tasks, including in some areas that traditionally require specialized skills, like computer programming.
他的动机是让任何熟悉军事问题空间, 的人，无论其技术背景如何,，都能推进他们对有用软件应用程序, 的想法，基本上绕过传统军事软件开发流程的时间和成本限制。林奇的目标是构建自己的应用程序，而尼斯则监控他使用该技术的经验。
His motivation was to empower anyone familiar with the military problem space, regardless of their technical background, to advance their ideas for useful software applications, essentially bypassing the time and cost constraints of the traditional military software development pipeline. Lynch aimed to build his own application while Niss monitored his experience with the technology.
"Phantom 学生想看看他是否可以在没有任何经验的情况下通过自我识别的振动编码, 创建一个有用的应用程序," Niss 说。 "在这个项目中,我想了解他对人工智能的看法如何随着时间的使用而改变。我们都想更好地了解军队中的非技术用户可以在何处以及如何使用人工智能。"
"The Phantom student wanted to see if he could create a useful application through self-identified vibe-coding, without any previous experience," Niss says. "Within this project, I wanted to understand how his perception of AI changed over time with use. We both wanted to understand better where and how AI could be used by nontechnical users in the military."
林奇开始研究,，从没有编码技能开始，使用聊天机器人,，他是否可以创建一个特定于他的战术团队类型的应用程序，以帮助减少附带损害，同时提高更广泛任务中的生存能力。该应用程序将提供包括人工智能辅助目标识别;模块化智能,监视,和侦察;自主打击;以及战场上的通信管理等功能。
Lynch set out to see if, starting with no coding skills and using chatbots, he could create an application specific to his type of tactical team to help reduce collateral damage while enhancing survivability in the broader mission. This application would offer capabilities including AI-assisted target recognition; modular intelligence, surveillance, and reconnaissance; autonomous striking; and communication management on the battlefield.
在项目期间, Lynch 完成了几门人工智能专业开发课程，并熟悉了该技术的军事和非军事用途。作为代码生成, 的基础，他使用了三个 AI 聊天机器人: Anthropic的 Claude, OpenAI的 ChatGPT, 和 Google的 Gemini 的付费模型。大部分工作仅通过网络浏览器, 上的聊天机器人 主要聊天功能完成，而不是像现在的标准那样作为开发环境, 内的集成系统。最终的应用程序是使用 Google AI Studio App, 生成的，它可以创建与 Gemini 应用程序编程接口交互的应用程序，并将 AI 集成到开发环境中。
During the project, Lynch completed several professional development courses in AI and familiarized himself with both military and nonmilitary uses of the technology. For the basis for his code generation, he used the paid models of three AI chatbots: Anthropic的 Claude, OpenAI的 ChatGPT, and Google的 Gemini. Most of this work was done only through the chatbots main chat function on a web browser, not as an integrated system within a development environment, as is standard now. The final application was produced using Google AI Studio App, which can create applications that interface with the Gemini application programming interface and has AI integrated in the development environment.
超过三个月的, Lynch 使用这些模型构建了他的应用程序,，称为远程操作模块化增强设备(ROMAD-AI)。在这段时间,他学会了几种改进代码输出的方法。例如,，他经常遇到人工智能聊天机器人缺乏分层焦点和修改不相关代码部分的困难。他发现将问题分解成小部分, 清晰地构建问题, 并在对话偏离目标太远时引导话题回到主题非常重要。
Over three months, Lynch worked with these models to build his application, called the Remote Operating Modular Augmentation Device (ROMAD-AI). During this time, he learned several methods to improve the code output. For example, he often encountered difficulties with the AI chatbots lacking hierarchical focus and modifying unrelated code sections. He discovered it was important to break problems into small parts, frame questions clearly, and steer conversations back on topic when they stray too far from the objective.
学习识别聊天机器人的局限性并有效地解决它们占据了项目时间的大部分时间。随着 Lynch 在聊天机器人, 方面获得更多经验，人工智能功能和开发时间的限制促使他重新调整了项目, 的范围，将其从可以在战场上提供帮助的应用程序转移到可以执行基本文档处理, 的应用程序，例如分析战场战术地图并通过与 VLM 支持的聊天机器人的接口生成任务规划文档。虽然最终的原型并未执行 Lynch 最初计划包含的所有功能 (，并且在其当前迭代中对于所需用例来说并不安全),，但它证明了此类应用程序对服务成员的功能和有用性。
Learning to recognize the chatbots limitations and effectively work around them took up most of the project timeline. As Lynch gained more experience with the chatbots, limitations in the AI capabilities and time for development caused him to re-scope the project, moving it from an application that could assist on the battlefield to one that could perform basic document processing, such as analyzing tactical maps of battlefields and generating mission-planning documents through an interface with a VLM-powered chatbot. While the resulting prototype did not perform all capabilities Lynch originally set out to include (and in its current iteration was not secure for the desired use case), it proved the capability and usefulness of such an application for service members.
"我对这个最终产品印象深刻,，它向我展示了这些系统在非专家的原型设计方面的强大能力," Niss 说。 "I'm 现在认为这些可以成为非技术专家向技术专家传达问题和可能的解决方案的强大工具, 并帮助传达期望的结果。"
"I was quite impressed with this final product, and it showed me how powerful these systems can be at prototyping designs from nonexperts," Niss says. "I'm now of the opinion that these can be powerful tools for nontechnical experts to convey problems and possible solutions to technical experts, and aid in communicating desired outcomes."
Niss 在他的经历中观察到了 Lynch 对 AI 语言模型的看法的变化。在以令人印象深刻的目标开始后, Lynch 了解了当前技术的功能，并在项目期结束时大幅降低了他的期望。 Lynch 和 Niss, 对他对不同 AI 系统随时间和系统更新的感知的测量特别感兴趣，其中 Claude 在可爱度, 拟人化, 和感知智力等特征上表现出比 ChatGPT 更高的稳定性。林奇发现人工智能是一位有用的导师,，但指出人工智能在他熟悉的主题上不准确。
Niss observed the change in Lynch的 perspective of AI language models during his experience. After starting with an impressive goal, Lynch gained understanding of the capabilities of current technology and significantly scoped down his expectations by the end of the project period. Measures of his perceptions of the different AI systems over time and across system updates were particularly interesting to Lynch and Niss, with Claude showing more stability than ChatGPT across traits such as likeability, anthropomorphism, and perceived intelligence. Lynch found AI to be a helpful tutor, but noted its inaccuracies on topics he knew well.
该项目表明，人工智能聊天机器人可以使非技术服务成员能够针对其独特的问题生成可行的软件应用程序,，尽管在处理敏感信息和关键应用程序时，它作为原型制作助手比作为完整的生产工具效果更好。代码审查不当可能会导致安全风险,，正如 Lynch 没有意识到最终应用程序将输入文档发送到 Gemini AI 模型来分析, 而不是在他的计算机上本地解析文档所证明的那样。 Although AI can generate significant amounts of functional code, code review remains a bottleneck in this space.
The project showed that AI chatbots can empower nontechnical service members to produce viable software applications for their unique problems, although it works better as a prototyping assistant than as a full production tool when handling sensitive information and for critical applications. Improper vetting of code may lead to security risks, as demonstrated by an instance where Lynch didn't realize that the final application was sending the input documents to a Gemini AI model to analyze, rather than parsing the documents locally on his computer. Although AI can generate significant amounts of functional code, code review remains a bottleneck in this space.
"对我来说, 这个项目加强了不同领域专家之间的交流," Niss 说。 "无论人工智能有多好,，我认为我们'总是需要合作，为最重要的问题找到最佳解决方案。"
"For me, this project reinforced the expanse between experts in different fields," Niss says. "No matter how good AI gets, I think we'll always need to collaborate to get to the best solutions for the most important problems."