Perplexity Profile picture
Dec 15, 2022 10 tweets 5 min read Read on X
Introducing Bird SQL, a Twitter search interface that is powered by Perplexity’s structured search engine. It uses OpenAI Codex to translate natural language into SQL, giving everyone the ability to navigate large datasets like Twitter.
perplexity.ai/sql
With Bird SQL, you can quickly find information on Twitter that would have been impossible to find with conventional search engines or web browsing:
"most liked tweets about #worldcup"
perplexity.ai/sql?uuid=9b03e…
Search through top content:
"most liked tweets of all time"
perplexity.ai/sql?uuid=05f6b…
Find new users to follow:
"top astrophysicists"
perplexity.ai/sql?uuid=1492d…
Filter down to content you’re curious about:
"tweets about chatGPT liked by Elon Musk"
perplexity.ai/sql?uuid=0a675…
Search your favorite topics:
"top posts about ChatGPT"
perplexity.ai/sql?uuid=ea707…
Analyze social graphs:
"People followed by Jeff Bezos who don’t follow him back"
perplexity.ai/sql?uuid=b37ef…
Analyze how people engage:
"people Sam Altman engages with the most"
perplexity.ai/sql?uuid=d4600…
If you are interested in using our search engine on your structured or unstructured data, contact us at support@perplexity.ai, our Discord server, or via Twitter. Join our Discord to learn more about search and large language models: discord.com/invite/kWJZsxP…
This is a demo, not a commercial product. There are limitations to our Twitter data, database performance, and the expressiveness of SQL. Bird SQL does not interpret the content of tweets. For unstructured search, try Perplexity Ask.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Perplexity

Perplexity Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @perplexity_ai

Feb 14
Introducing Deep Research on Perplexity.

Deep Research lets you generate in-depth research reports on any topic.

Available to everyone for free—up to 5 queries per day for non-subscribers and 500 queries per day for Pro users.
Perplexity Deep Research surpasses leading models in performance—scoring 93.9% accuracy on the SimpleQA benchmark. Image
Deep Research on Perplexity scores 21.1% on Humanity’s Last Exam, outperforming Gemini Thinking, o3-mini, o1, DeepSeek-R1, and other top models.

We also have optimized Deep Research for speed. Image
Read 7 tweets
Feb 11
Perplexity's Sonar—built on Llama 3.3 70b—outperforms GPT-4o-mini and Claude 3.5 Haiku while matching or surpassing top models like GPT-4o and Claude 3.5 Sonnet in user satisfaction.

At 1200 tokens/second, Sonar is optimized for answer quality and speed.
Sonar significantly outperforms GPT-4o-mini and Claude 3.5 Haiku in user satisfaction.

It also surpasses Claude 3.5 Sonnet and nearly matches GPT-4o, doing so at a fraction of the cost and over 10x faster. Image
Powered by Cerebras inference infrastructure, Sonar delivers answers at blazing fast speeds, achieving a decoding throughput that is nearly 10x times faster than comparable models like Gemini 2.0 Flash. Image
Read 5 tweets
Jan 23
Introducing Perplexity Assistant.

Assistant uses reasoning, search, and apps to help with daily tasks ranging from simple questions to multi-app actions. You can book dinner, find a forgotten song, call a ride, draft emails, set reminders, and more.

Available on Play Store.
Perplexity Assistant browses the web to complete tasks for you. For example, if you want to be reminded of a public event, it will find the correct time and date and set an intelligent reminder.
It also maintains context from one action to another — if you’re researching restaurants in your area and want to reserve a table, choose an option and Assistant will help book it.
Read 5 tweets
Jan 21
Introducing Sonar: Perplexity’s API.

Sonar is the most affordable search API product on the market. Use it to build generative search, powered by real-time information and citations, into your apps. We’re also offering a Pro version with deeper functionality. Image
With Sonar Pro, develop capabilities that are even more powerful, supporting advanced, in-depth queries and follow up questions. Image
Companies that have integrated Sonar have seen big wins — such as Zoom, which uses Perplexity’s API to strengthen native search in their AI Companion 2.0 product. Image
Read 5 tweets
Apr 23, 2024
We’re excited to announce that we’ve raised $62.7 million in a Series B1 funding led by Daniel Gross. The round also includes Stanley Druckenmiller, NVIDIA, Jeff Bezos, Tobi Lutke, Garry Tan, Andrej Karpathy, Dylan Field, Elad Gil, Nat Friedman, IVP, NEA, Jakob Uszkoreit, Naval Ravikant, Brad Gerstner and Lip-Bu Tan.
Since we announced our Series B in January 2024, we’ve grown to serve 169M queries per month, and more than 1 billion queries in the last 15 months. The additional funding will be used to support our continued consumer adoption and enterprise expansion.
We’ve inked new partnerships with two of the world’s largest telecommunications firms — Japan’s SoftBank (SFTBY:US) and Germany’s Deutsche Telekom (ETR:DTE) — to distribute Perplexity to a combined total of over 116M users. As global telecom leaders increasingly seek to bring AI tools to their mobile subscribers, Perplexity has become the partner of choice.
Read 4 tweets
Feb 15, 2023
When building *answer engines*, truthfulness is essential when delivering direct answers to questions. Just being able to cite your sources isn't sufficient. Hence why we're excited about giving you the power to curate your sources. Few more examples in 🧵 of what it lets you do
“Yann LeCun” on @perplexity_ai: something for which you would expect to see an accurate bio of @ylecun is incorrect. Says “he is the cofounder and advisor for @Meta”. Error stems from his Linkedin page having keywords like “cofounder”. Left: Incorrect, Right: Correct.
We also allow you to add more sources that lets you add more details and give you the analogous experience of scrolling through search engines, while being on an answer engine.
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(