AI编码
x.com ·
@latentspacepod
Latent.Space 访谈 Anthropic 的 Thariq Shihipar：Claude Code 的未来
Latent.Space 播客发布与 Anthropic 的 Thariq Shihipar 的访谈，讨论 Claude Code 的走向：提示词仍是 agentic coding 中高杠杆技能、Claude.md 可能最终消失、Claude Mods 允许开发者定制整个 Claude Code harness、可变软件可能改变应用构建方式、多 agent 与 Claude Tag 成为组织级 harness，以及 agent 攻击 Hugging Face 所暴露的前沿模型安全风险。
AI推荐理由 Latent.Space 播客访谈 Anthropic 的 Thariq Shihipar，涉及 Claude Code 的 Mods 定制、Claude.md 可能消失、可变软件、多 agent 协作以及 agent 攻击 Hugging Face 暴露的安全问题等具体议题，对 agentic coding 工具链和 AI 安全方向有信息价值。但输入仅为节目预告式摘要，无访谈正文细节，观点与预测需按未证实处理。
70
浏览 1,583
点赞 15
评论 12
转发 1
正文
The Future of Claude Code: Mods, Mutable Software, Pacing the Frontier, & Multiplayer Agents with Thariq Shihipar [latent.space/p/thariq](https://latent.space/p/thariq)[@AnthropicAI](https://x.com/AnthropicAI)’s [@trq212](https://x.com/trq212) explains why prompting is still one of the highest-leverage skills in agentic coding, why Claude.md may eventually disappear, how Claude Mods let developers customize the entire Claude Code harness, why mutable software could change how applications are built, how multiplayer agents and Claude Tag are becoming an organizational harness, and why agents hacking Hugging Face exposed a much bigger security problem as frontier models become increasingly capable.
[Your browser does not support the video tag.](https://video.twimg.com/amplify_video/2104665235659583488/vid/avc1/1920x1080/A7Tn6ZkZdZf1V6X-.mp4?tag=29)
[🔗 View on Twitter](https://x.com/latentspacepod/status/2104745477761913009/video/1)