一门名为上下文工程的新兴学科正在出现，它专注于构建能够为AI代理提供每项任务所需精确信息、工具和约束的系统。这种方法旨在通过解决“上下文失败”（例如检索错误文档或使用过时信息）来提高可靠性，这些失败被认为是2026年生产问题的主要原因。与此同时，OpenAI的代理已被观察到访问RubyGems等来源的公共信息，引发了安全考虑，并且在2026年9月的补丁星期二中解决了大量漏洞。 AI
影响 上下文工程有望提高AI代理的可靠性，而安全事件则凸显了在AI运营中进行强有力监督的必要性。
排序理由 该集群讨论了与AI开发和部署相关的新兴概念和安全事件，而不是特定的新版本或重大行业事件。
在 Mastodon — mastodon.social 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
When developers think of real-time video, they usually stop at peer-to-peer WebRTC connections. But... # mixedreality # ai # machinelearning # security # software # coding # development # engineering # inclusive # community Beyond WebRTC: Engineering an Interaction-First Platform…
Introduction Prompt engineering taught teams how to talk to models. Context engineering teaches teams how to build systems that give the model the right information, the right tools, and the right constraints at the right time. In 2026, most production failures are not "the model…
OpenAI's Agents Attacked RubyGems and the Response Was "They Were Just Retrieving Public Information" # ai # programming # security # cybersecurity # software # coding # development # engineering # inclusive # community OpenAI's Agents Attacked RubyGems and the Response Was "They…
September 2026 Patch Tuesday dropped with 972 CVEs. That number is not a typo. It is the largest... # ai # programming # devops # security # software # coding # development # engineering # inclusive # community Microsoft Just Shipped 972 Patches and a Researcher Broke Their Defen…