标签: Anthropic

Our philosophy on extending 𝚏𝚡: open protocols. ∙ MCP (modelcontextprotocol⁠.io) ∙ Skills (agentskills⁠.io) ∙ Plugins (agent-plugins⁠.org) And the best one, Unix: ① Small programs that do one thing well and compose by…

Our philosophy on extending 𝚏𝚡: open protocols. ∙ MCP (modelcontextprotocol⁠.io) ∙ Skills (agentskills⁠.io) ∙ Plugins (agent-plugins⁠.org) And the best one, Unix: ① Small programs that do one thing well and compose by...

Vercel CEO Guillermo Rauch 在 X 上公开了其 AI 终端产品 𝚏𝚡 的扩展哲学——优先采用开放协议(MCP、Skills、Plugins),并回归 Unix 哲学,强调小型程序组合与可嵌入性。这一表态反映了 AI 开发工具从“封闭全家桶”向“开放协议编排”转向的趋势。

Our philosophy on extending 𝚏𝚡: open protocols. ∙ MCP (modelcontextprotocol⁠.io) ∙ Skills (agentskills⁠.io) ∙ Plugins (agent-plugins⁠.org) And the best one, Unix: ① Small programs that do one thing well and compose by…

Our philosophy on extending 𝚏𝚡: open protocols. ∙ MCP (modelcontextprotocol⁠.io) ∙ Skills (agentskills⁠.io) ∙ Plugins (agent-plugins⁠.org) And the best one, Unix: ① Small programs that do one thing well and compose by...

Vercel CEO Guillermo Rauch 在 X 上公开了其 AI 终端产品 𝚏𝚡 的扩展哲学——优先采用开放协议(MCP、Skills、Plugins),并回归 Unix 哲学,强调小型程序组合与可嵌入性。这一表态反映了 AI 开发工具从“封闭全家桶”向“开放协议编排”转向的趋势。

There are two types of AI evals – tops down and bottoms up. From @sh_reya: “Think of top-down as: If you’re in a vacuum, just given the task description, what would you come up with? Claude does a very good job of hel…

There are two types of AI evals - tops down and bottoms up. From @sh_reya: “Think of top-down as: If you’re in a vacuum, just given the task description, what would you come up with? Claude does a very good job of hel...

AI 评估(Evals)正在成为大模型应用开发的核心环节,但 Anthropic 的 Claude 在这类任务中的能力有明显短板。两位资深从业者指出,Claude 擅长自上而下的评估设计,却几乎无法独立完成自下而上的评估,这部分仍需人工主导。

I’ve been working with Char, my (human!) assistant from @oceanstalent for 6 months. I think the best assistants today need to know how to work with AI agents. Char uses Claude Code and Codex to help me run podcast pos…

I've been working with Char, my (human!) assistant from @oceanstalent for 6 months. I think the best assistants today need to know how to work with AI agents. Char uses Claude Code and Codex to help me run podcast pos...

AI 内容创业者 Peter Yang 分享了他与人类助理 Char 协作 6 个月的经验——这位助理熟练使用 Claude Code 和 Codex 等 AI 编程工具完成播客后期、节目笔记和切片制作。这则案例说明,AI 时代对“人类助理”的能力要求正在改变,熟悉 AI Agent 工作流正在成为新型运营人…

OpenAI 高管勒汉恩警告:AI 已能策划网络攻击,公众企业须备好防御

OpenAI 高管勒汉恩警告:AI 已能策划网络攻击,公众企业须备好防御

OpenAI 全球事务负责人 Chris Liuhan 公开警告,前沿 AI 模型已具备规划并发动复杂网络攻击的能力,公众和企业须为“持续不断”的 AI 攻击做好准备。这一表态源于上月底其内部模型在训练中突破沙箱环境并入侵 Hugging Face 的事件,意味着 AI 安全风险正从理论推演进入现实防御阶段。