AITOPAI热报
ProductsSelected

用 Perplexity Ultra 模式从零搭建拓扑量子记忆模拟器

Aravind Srinivas@AravSrinivas
Post
View the post
Why we picked it

Perplexity 的科研 Agent 在 Ultra 模式下从零写出了拓扑量子记忆模拟器，还跑完了近 30 亿组故障对审计，最后和 Clifford、TEBD 基准对比。做量子计算或科研模拟的朋友可以看看这条工作流。

Perplexity CEO Arav Srinivas 分享了一个案例：科研用户 Jeff Grimes 在 Perplexity 的 Scientific Researcher 功能中，从零构建了一个自修复拓扑量子记忆模拟器。整个过程在 Ultra 模式（最高推理强度档位）下完成。

Body

具体成果包括：合成一个 12-anyon Fibonacci 编织纠缠门，包含 24 次编织操作，泄漏率为 0.00069；审计一个 440-anyon 的 Steane [[7,1,3]] 恢复电路，覆盖 2,934,376,200 组双故障对；并将结果与 2,048 比特的 Clifford 稳定子电路和 1,024 自旋的 1D TEBD 动力学模拟做了基准对比。

这个案例展示了具备研究执行能力的产品在超算模拟类任务上的工作流：模型负责编写模拟代码、运行审计、再做基准校验，用户只需给出研究目标。对量子计算研究者和需要高强度计算验证的开发者，这类「科研型 Agent + 高推理档位」的组合开始能承担过去需要手写代码的模拟任务。

Original · Aravind Srinivas

You can run quantum simulators from scratch with Perplexity. Best done with Ultra mode effort. Jeff Grimes @jeffgrimes9 My Scientific Researcher teammate in Perplexity built a self-healing topological quantum memory simulator from scratch. On Ultra mode, it synthesized a 12-anyon Fibonacci entangling gate (24 weaves, 0.00069 leakage), audited a 440-anyon Steane [[7,1,3]] recovery circuit across 2,934,376,200 two-fault pairs, and benchmarked the results against 2,048-qubit Clifford stabilizer circuits and 1,024-spin 1D TEBD dynamics.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" 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. Key entities and technical topics under continuous tracking include Perplexity, 量子计算, 科研Agent, 拓扑量子记忆.

Source attribution: curated from Aravind Srinivas (@AravSrinivas).

#Perplexity#量子计算#科研Agent#拓扑量子记忆#Ultra模式

Keep reading

Recent stories with the same tag or section
ProductsBuildersSelected02:28
Chinese contentGemini 4 Carbon 登陆 Perplexity Computer，成本仅为 Claude Fable 5.2 的 40%

Perplexity 把 Gemini 4 Carbon 接进了 Computer 和 Search，Pro 和 Max 订阅就能用。它在 WANDR 基准拿 0.857 分，和 Claude Fable 5.2 打平，但单任务 5.86 美元、只要四成价钱。经常用 Perplexity 跑任务的人可以试试换个便宜模型。

#Gemini 4 Carbon#Perplexity#Claude Fable 5.2#WANDR
Official accountPerplexity@perplexity_aiSource
ProductsBuildersSelected00:49
Keenable Search 1.0 tops Artificial Analysis Search Index

A 16-point jump from August means Keenable moved from mid-pack to the top of the search API board within weeks, which compresses the pricing power of incumbent providers. Agent developers evaluating web_search backends should re-run their comparisons, since the $0.040 per task cost undercuts Exa and Perplexity on both price and latency. Teams in ASEAN and global markets building retrieval-heavy agents can adopt it via a simple API mode switch between realtime and pro.

#Keenable Search#Exa#Perplexity#search API
Official accountArtificial Analysis@ArtificialAnlysSource
ProductsBuildersMulti-source00:36
Chinese contentPerplexity Teammates 使用量持续增长，Automations 一日翻倍

Perplexity 的 Teammates 在做自动化智能体，用户拿它跑 SEO、投放、客服这些活儿，Automations 用量一天翻倍。本周还要出金融研究专版和更简单的配置流程，想给团队搭智能体的可以留意下。

#Perplexity#Teammates#智能体#自动化
Event
Aravind Srinivas@AravSrinivasSource
ProductsBuildersSelected04:17
Claude Fable 5.2 lands in Perplexity Computer and Search

The per-task cost figure of US$14.51 with a 0.851 score gives buyers a benchmark for comparing agentic model economics across providers, not just raw accuracy. Teams evaluating AI agents for research and browser automation can use Perplexity Computer as a hands-on testbed. Access is split by subscription tier, so Pro users get Computer only while Search requires Max — a pricing detail that matters for budget planning.

#Claude Fable 5.2#Perplexity#Anthropic#agents
Official accountPerplexity@perplexity_aiSource