报告称微软 Copilot 承包商可完整查看用户上传的照片、AI 提示词等
IT之家 9 月 30 日消息,科技媒体 404 Media 于 9 月 28 日披露一份内部文件, 报道称数百名受雇于微软的合同工,能够看到用户上传的含有清晰面部信息的照片,以及相关提示词和 AI 生成的编辑结果。 该媒体记者约瑟夫 · 考克斯(Joseph Cox)在调查后指出,这些合同工可以看…
IT之家 9 月 30 日消息,科技媒体 404 Media 于 9 月 28 日披露一份内部文件, 报道称数百名受雇于微软的合同工,能够看到用户上传的含有清晰面部信息的照片,以及相关提示词和 AI 生成的编辑结果。 该媒体记者约瑟夫 · 考克斯(Joseph Cox)在调查后指出,这些合同工可以看…
IT之家 8 月 27 日消息,Adobe 今日宣布为 Photoshop 新增“AI Assisted Editor”(AI 辅助编辑器)测试体验。 该功能采用基于自然语言提示词的编辑方式,提供简化版操作界面,用户无需使用传统复杂工具即可完成图像修改。 AI 辅助编辑器作为 Photoshop 中…
用pytest风格测试LLM提示词,Crilio让AI输出验证变得可编程。
Article URL: https://github.com/mukundzha/crilio Comments URL: https://news.ycombinator.com/item?id=49433864 Points: 5 # Comments: 0
格式与提示词微观调整如何影响大模型编码表现?这项对照实验给出可复现的优化路径。
arXiv:2608.21074v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in research workflows and software development pi…
同一提示词换个词性能骤变,这项研究首次从n-gram词元级别系统拆解LLM的提示词敏感性,帮你避开微调陷阱。
arXiv:2608.20349v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit extreme sensitivity to surface-level prompt variations, in whic…
LLM提示词压缩新思路:生成式方法SCOPE,有效压缩上下文同时保留性能,COLM 2026收录。
arXiv:2508.15813v2 Announce Type: replace-cross Abstract: A big issue in modern LLM applications is they tend to feed long context to LLM, which resul…
用创业者的成本思维使用Claude:缓存不变的系统提示词与工具定义,输入成本能降到约十分之一。
I am running an AI-native startup. Early on though, I would spend so much time staying ahead of every new AI hot take that I lost focus on what I need…
受够了AI的标题党腔调?这个开源项目让Claude回归正经说话。
Article URL: https://github.com/adnanakil/nobuzz/blob/main/README.md Comments URL: https://news.ycombinator.com/item?id=49388752 Points: 251 # Comment…
变异测试一招揪出LLM评测漏洞,Muteval让评估数据更可靠,开源免费直接上手。
Article URL: https://github.com/AshwinUgale/muteval Comments URL: https://news.ycombinator.com/item?id=49388918 Points: 1 # Comments: 0
别再把AI泄密当玩笑,聊天机器人能被套出系统提示词,这不是越狱而是侦察。
An AI assistant got talked into describing its own guts to a stranger. That's not a jailbreak curiosity, that's reconnaissance-as-a-service, and it sh…
用漫画轻松搞懂Claude的聊天、协作与编程,零基础也能秒懂AI用法
Article URL: https://github.com/Fake4d/claude-school Comments URL: https://news.ycombinator.com/item?id=49356989 Points: 1 # Comments: 0
同一问题换个问法,大模型对事实与信念的判断就不同,这份研究揭示了提示词如何影响模型的认知边界。
arXiv:2608.17809v1 Announce Type: new Abstract: Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "…
用列文-柯尔莫哥洛夫复杂度度量提示词价值,给“好提示”一个可计算的理论标尺。
arXiv:2608.16438v1 Announce Type: new Abstract: In a world where valuable artifacts are increasingly created, completed, or processed by LLMs, the cen…
针对LLM智能体的提示词优化新方法,把约束条件纳入优化过程,让Agent更懂规则、少犯错。
arXiv:2608.16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use …
把大模型提示词写成语言语法,用编程方式直调AI工具,新思路值得一看
Article URL: https://github.com/amaldini/maldalang Comments URL: https://news.ycombinator.com/item?id=49331723 Points: 2 # Comments: 0
用大模型“幻觉”替代死板分类,自动生成标签,让内容管理更灵活高效。
Don't classify. Hallucinate! I still have quite a bit of older content on my blog that I never got round to tagging. My blog has 1,856 tags - lik…
AI缓存让重复对话成本骤降,命中价仅为未命中的五十分之一,十分钟内免重算,省钱关键必看。
这里记录每周值得分享的科技内容,周五发布。...
手把手教你在GitHub Copilot应用中写出第一个提示词,快速上手AI编程助手。
Learn how to write your first prompt in the GitHub Copilot app, choose the right context and model, and start your first task with confidence. The pos…