Perplexity AI 已将其新的“Computer 中的深度研究”功能作为一项原生技能集成到其 Computer 产品中。此功能利用“搜索即代码”架构，使模型能够生成代码，该代码可以为特定查询编排数千个并行检索步骤。该公司表示，这项新功能在所有基准测试中都超越了以前的深度研究功能，并且现在可供 Pro 和 Max 订阅者使用。 AI
影响 通过新颖的代码生成方法增强 Perplexity 的 AI 搜索能力，以进行更深入、更量身定制的研究。
排序理由 现有 AI 驱动工具的产品集成和功能更新。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Learn more about Deep Research in Computer: https://t.co/YhFZVvTb3j
Deep Research in Computer is built on our Search as Code architecture. The model writes code that assembles search itself, running thousands of retrieval steps in parallel, tailored to each question. It outperforms legacy Deep Research on every benchmark. https://t.co/0BrQjt8iG…
We're integrating Deep Research as a native skill inside Computer. It now connects to the agent harness that powers Computer, with access to search as code generation, long running sandboxes, connectors, tools, and licensed data. Available now to Pro and Max subscribers. https:…