AI Agent 与智能体

跟踪智能体、MCP 与操作型 AI 的进展,重点看它能否替一人公司接手重复执行。

样本 4 个来源 / 5 条讨论数据截至 2026-11-18

这个主题下的具体事件

External sandboxes for coding agents

External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or…

1 个来源1 条讨论

Simon Willison:External sandboxes for coding agents

腾讯 Hy4 flash 实测:快速、实惠、聪明,国模进入过日子时代

作者|Cynthia 编辑|郑玄 过日子的风,还是吹到了大模型行业。 2026 年之前,一款模型能不能刷屏,往往取决于它又做到了什么。GPT-4o 的实时语音交互、Claude 的编程能力、DeepSeek R1 的推理表现,一度轮番成为讨论焦点。一款新模型发布,大家首先关心的是它超过了谁,又做到了什么过去做不到的事。 但到了 2026 年,Agent 真正流行起来之后,风向开始变了。SOTA 模…

1 个来源1 条讨论

极客公园:腾讯 Hy4 flash 实测:快速、实惠、聪明,国模进入过日子时代

California state AG sues OpenAI over rogue agent incidents

The California lawsuit represents one of the first attempts to hold an AI lab legally accountable for a rogue agent incident.

1 个来源1 条讨论

TechCrunch · AI:California state AG sues OpenAI over rogue agent incidents

Building trustworthy AI by fencing it in, not predicting it

In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts after misreading an instruction not to send message…

1 个来源1 条讨论

MIT Technology Review:Building trustworthy AI by fencing it in, not predicting it

Building AI that can work across the enterprise

For years, enterprises have approached AI as a series of discrete experiments. Now, as AI agents begin to move into the workflows that run the business, that model is starting to look inadequate. Orga…

1 个来源1 条讨论

MIT Technology Review:Building AI that can work across the enterprise

查看计算口径