PapersMulti-source

Perplexity 发布 CobbleDB 研究

Why we picked it

Perplexity 发表了他们构建 CobbleDB 的研究,这个数据库是他们的搜索服务的关键部分,由两位工程师和数百个 AI 代理在两个月内完成。

Perplexity 发布了关于其用于搜索服务的键值数据库 CobbleDB 的研究。该数据库由两位工程师和数百个 AI 代理在两个月内构建。研究详细介绍了核心基础设施的构建过程。

Original · Perplexity

We’re publishing research on how we built CobbleDB, our key-value database that serves web content for Perplexity search. Two engineers and a team of hundreds of proactive, always-on AI agents built the core infrastructure in two months.📊 17 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Perplexity, CobbleDB, 数据库, AI代理.

Source attribution: curated from Perplexity (@perplexity_ai). Cross-source corroboration: 3 independent sources have covered this development (including Aravind Srinivas, shao__meng), confirming industry-wide signal strength.

  • Aravind Srinivas09-15 20:23Source
  • shao__meng09-16 02:00Source