Perplexity AI
Company type | Private |
---|---|
Industry | Artificial intelligence |
Genre | Search engine |
Founded | August 2022 |
Founders |
|
Headquarters | , US |
Key people | Aravind Srinivas (CEO) |
Products |
|
Services |
|
Number of employees | 55[3] (2024) |
Perplexity AI | |
| |
Website | www |
Perplexity AI is a conversational search engine that uses large language models (LLMs) to answer queries. Its developer, Perplexity AI, Inc., is based in San Francisco, California.
Founded in 2022, Perplexity generates answers using sources from the web and cites links within the text response.[4] Perplexity works on a freemium model; the free product uses the company's standalone LLM, while the paid version Perplexity Pro has access to GPT-4, Claude 3.5, Mistral Large, Llama 3 and an Experimental Perplexity Model.[1][4][3] In Q1 2024, it had reached 15 million monthly users.[5]
History
[edit]Perplexity was founded in 2022 by Aravind Srinivas, Andy Konwinski, Denis Yarats and Johnny Ho, engineers with backgrounds in back-end systems, artificial intelligence (AI) and machine learning:
- Srinivas, the CEO (Chief executive officer), worked at OpenAI as an AI researcher.
- Konwinski was among the founding team at Databricks.
- Yarats, the CTO (Chief technology officer), was an AI research scientist at Meta.
- Ho, the Chief Strategy Officer, worked as an engineer at Quora, then as a quantitative trader on Wall Street.[6]
As of 2024, Perplexity has raised $165 million in funding, valuing the company at over $1 billion.[3] Investors include Jeff Bezos, Nvidia, Databricks, Bessemer Venture Partners, Susan Wojcicki, Jeff Dean, Yann LeCun, Andrej Karpathy, Nat Friedman, and Garry Tan.[7][8][3]
In mid-2024, Perplexity reached a 3 billion USD valuation.[9]
Functionality
[edit]Perplexity's main product is its search engine, which relies on large language models.[7] It uses the context of the user queries to provide a personalized search result. Perplexity summarizes the search results and produces a text with inline citations.[7]
Perplexity's paid variant, the "Pro" mode (formerly Copilot), asks the user clarifying questions to refine queries. It enables users to upload and analyze local files, including images, alongside generating images using AI. Additionally, it provides access to an API.[7]
Perplexity launched a new enterprise version of its product in April 2024.[3]
In May 2024, Perplexity launched a new feature called Pages, which generates a customizable webpage based on user prompts. Pages uses Perplexity’s AI search models to gather information and create a research presentation that can be published and shared with others.[10]
Technology
[edit]Perplexity gives users the ability to select from multiple LLMs including Perplexity's in-house models, which are open-source LLMs that they have extended and retrained.[11] Some of these LLM options include:
- ChatGPT-4o[12]
- ChatGPT-3.5
- Claude 3.5 Sonnet[12]
- Claude 3 Opus[12]
- pplx-7b-online, an in-house model based on mistral-7b[11]
- pplx-70b-online, an in-house model based on llama2-70b[11]
- Sonar Large, an in-house model based on LlaMa3.1 70B[12]
Controversies
[edit]In June 2024, Forbes publicly criticized Perplexity for use of their content. According to Forbes, Perplexity published a story which was largely copied from a proprietary Forbes article, without mentioning or prominently citing Forbes. In response, Srinivas said that the feature had some "rough edges" and accepted feedback, but maintained that Perplexity only "aggregates" rather than plagiarizes information.[13][14]
Later that month, separate investigations by the magazine Wired and web developer Robb Knight found that Perplexity does not respect the robots.txt standard, which allows websites to stop web crawlers from scraping content, reportedly despite Perplexity claiming the opposite. Perplexity also lists the IP address ranges and user agent strings of their web crawlers publicly, but according to Wired and Robb Knight, they use undisclosed IP addresses and spoofed user agent strings when ignoring robots.txt.[15][16] In response, Srinivas stated in a phone interview that "Perplexity is not ignoring the Robot Exclusions Protocol... We don't just rely on our own web crawlers, we rely on third-party web crawlers as well." Srinivas explained that the web crawler identified by Wired was owned by a third-party provider.[17] Wired also stated that, in some cases, Perplexity may be summarizing "not actual news articles but reconstructions of what they say based on URLs and traces of them left in search engines like extracts and metadata, offering summaries purporting to be based on direct access to the relevant text."[15] When asked whether Perplexity would cease scraping Wired content using third parties, Srinivas responded that "it's complicated."[17]
Amazon Web Services, which hosts the Perplexity crawler, has a terms of service clause prohibiting its users from ignoring the robots.txt standard. Amazon began a "routine" investigation into the company's usage of Amazon Elastic Compute Cloud.[18]
In July 2024, Perplexity announced the launch of a new publishers' program to share ad revenue with partners.[19]
In October 2024, The New York Times (NYT) sent a cease-and-desist notice to Perplexity to stop accessing and using NYT content, claiming that Perplexity is violating its copyright by scraping data from its website.[20] NYT is also suing OpenAI and Microsoft for copyright infringement for similarly using millions of its articles to train the large language models that power ChatGPT.[21] The cease-and-desist notice sent by NYT lawyers read in part: "Perplexity and its business partners have been unjustly enriched by using, without authorization, The Times's expressive, carefully written and researched, and edited journalism without a license."[22] Perplexity plans to respond to the notice by October 30, 2024.[20] The same month, Dow Jones and New York Post filed a lawsuit against Perplexity, alleging copyright infringement. The lawsuit also alleges that Perplexity attributed quotes to an article on F-16 jets for Ukraine that never appeared in the original article.[23]
References
[edit]- ^ a b "Startup Perplexity Challenges Google With AI Search". The Wall Street Journal. January 4, 2024. Archived from the original on 2024-01-10. Retrieved 2024-01-10.
- ^ "Perplexity Free based on GPT-3.5". discord.com. Perplexity Community Moderator "IceLavaMan". Retrieved 8 October 2024.
- ^ a b c d e Ghaffary, Shirin (2024-04-23). "AI Search Startup Perplexity Valued at $1 Billion in Funding Round". Bloomberg News. Archived from the original on 2024-04-24.
- ^ a b Singh, Shubham (2024-01-06). "Perplexity AI raises $73.6M in funding round led by Nvidia, Bezos, now valued at $522M". Business Today. Retrieved 2024-01-15.
- ^ Goode, Lauren (2024-03-21). "Perplexity's Founder Was Inspired by Sundar Pichai. Now They're Competing to Reinvent Search". Wired (magazine). Archived from the original on 2024-07-16. Retrieved 2024-07-27.
The startup says its user base has grown to 15 million active users, growing 50 percent from the 10 million reported just two months ago.
- ^ "AI-powered search engine Perplexity AI lands $26M, launches iOS app". TechCrunch. 2023-04-04. Archived from the original on 2024-03-05. Retrieved 2024-05-05.
- ^ a b c d Wiggers, Kyle (2024-01-04). "AI-powered search engine Perplexity AI, now valued at $520M, raises $73.6M". TechCrunch. Archived from the original on 2024-01-07. Retrieved 2024-01-07.
- ^ "Announcing our series A funding round and mobile app launch". Perplexity.ai. 2023-04-28. Archived from the original on 2024-04-22. Retrieved 2024-04-24.
- ^ "SoftBank to invest in search startup Perplexity AI at $3 bln valuation". Reuters. 2024-06-27. Archived from the original on 2024-08-02. Retrieved 2024-08-02.
Japanese technology investor SoftBank Group Corp's (9984.T), Vision Fund 2 is investing between $10 million and $20 million in U.S. search startup Perplexity AI at a valuation of $3 billion, Bloomberg News reported on Thursday.
- ^ David, Emilia (2024-05-30). "Perplexity will research and write reports". The Verge. Archived from the original on 2024-06-20. Retrieved 2024-06-24.
- ^ a b c "Introducing PPLX Online LLMs". Nov 29, 2023. Retrieved 6 November 2024.
- ^ a b c d "What advanced AI models are included in a Perplexity Pro subscription?". Retrieved 6 November 2024.
- ^ O'Brien, Matt (15 June 2024). "AI startup Perplexity wants to upend search business. News outlet Forbes says it's ripping them off". Associated Press. Archived from the original on 20 June 2024. Retrieved 20 June 2024.
- ^ Lane, Randall (11 June 2024). "Why Perplexity's Cynical Theft Represents Everything That Could Go Wrong With AI". Forbes. Retrieved 20 June 2024.
- ^ a b Mehrotra, Dhruv; Marchman, Tim (19 June 2024). "Perplexity Is a Bullshit Machine". Wired. Archived from the original on 20 June 2024. Retrieved 20 June 2024.
- ^ "Perplexity AI Is Lying about Their User Agent". Robb Knight. 15 June 2024. Archived from the original on 20 June 2024. Retrieved 20 June 2024.
- ^ a b Sullivan, Mark (June 21, 2024). "Perplexity CEO Aravind Srinivas responds to plagiarism and infringement accusations". Fast Company. Retrieved June 24, 2024.
- ^ Mehrotra, Dhruv; Couts, Andrew (June 27, 2024). "Amazon Is Investigating Perplexity Over Claims of Scraping Abuse". Wired. Retrieved July 3, 2024.
- ^ Robison, Kylie (2024-07-30). "Perplexity is cutting checks to publishers following plagiarism accusations". The Verge. Retrieved 2024-08-04.
- ^ a b Davis, Wes (2024-10-15). "The New York Times warns AI search engine Perplexity to stop using its content". The Verge. Retrieved 2024-10-17.
- ^ Complaint, New York Times, Co. v. Microsoft Corp., No. 1:23-cv-11195 (S.D.N.Y. Dec. 27, 2023).
- ^ Bruell, Alexandra (October 15, 2024). "New York Times to Bezos-Backed AI Startup: Stop Using Our Stuff". The Wall Street Journal. Retrieved October 17, 2024.
- ^ Bruell, Alexandra (October 21, 2024). "Wall Street Journal, New York Post Sue AI Startup Perplexity, Alleging 'Massive Freeriding'". The Wall Street Journal. Retrieved October 21, 2024.