Perplexity CEO Aravind Srinivas 在 20VC 访谈中表示，单个重度用户的算力消耗如今可媲美一个小团队。他举例称 Meta 等公司每位工程师在编码工具上年花费约 1000 万美元，Perplexity Computer 有用户每月支出超 1 万美元，其业务依靠智能体循环运转，公司内部也有人搭建多层智能体架构，用量远超普通用户。
Aravind Srinivas (CEO Perplexity): how a single power user can now consume as much compute as an entire small team.
"There are real engineers at Meta and other companies spending around $10 million a year per engineer on these coding tools.
There are users in Perplexity Computer, who spends upwards of $10,000 a month. Their business runs using agent loops that are running inside these harnesses.
Even internally inside our own company, there are some people who have set up these kinds of multi-agent hierarchies and agent loops that look like their own software architecture. I often ask these people to come explain to the rest of the company, “Hey, what are you doing with these tools? You clearly are consuming them way more than what we thought the average person in the company would do.”
---
The old software instinct was to chase a billion people doing small actions.
Agentic AI changes that math because one skilled operator can create a stream of machine work that runs all day.
----
On "20VC with Harry Stebbings" YouTube channel (
@HarryStebbings ), link in comment
Power users are driving consumer AI market growth. The top 1% of US consumer AI payers average $903 a month, while flat plans hold the median at $25. One top-1% payer spends as much as roughly 59 bottom-half payers, on average. Median spend has barely moved, while average spend in the top 1% climbed from $504 to $903 a month between January 2025 and August 2026. Model labs are better placed than apps built on their models to capture consumer AI's top 1% of spenders. Those users average $903 a month, up from $504, and most of it buys model usage. A lab pays only its serving cost for that usage, while an app pays API prices. Anthropic earlier said one $200 Max subscriber ran up tens of thousands of dollars in usage, a bill no API-paying app could absorb. Apps that want this tier have to own more of the model, as Cursor began doing with its Composer coding model.在 X 查看被引用的帖子
来源：Rohan Paul · x.com