Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

just used the Perplexity's Perplexity Labs. one question - 14 minutes - 53 sources - chain of tasks - used python to plot graphs wrote a complete thesis on the topic. better than any economist with decades of experience would. with proper plot in trends, data, etc. Aravind Srinivas

dev

10,718 subscribers

165,419 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 8

Фото профиля Lab4crypto

Lab4crypto1 год назад

🚀 Don't gamble with your portfolio! Use our advanced hybrid quant risk tool using on/off-chain data and make informed decisions. 📈 Acess to 1000+ charts for your crypto journey. 📚Join our Premium Telegram for daily alerts. 📊+21 projects supported. 🏗️ Beginners and experts.

Фото профиля Maxime Batandeo

Maxime Batandeo1 год назад

@perplexity_ai Don’t want to dunk on anyone but the what should be more impressive than the how. What is the insight you achieved to derive using this ? How does that fill the knowledge gap ?

Фото профиля z.

z.1 год назад

@perplexity_ai how does it compare to chatgpt deep research?

Фото профиля dev

dev1 год назад

every piece of the answer is generated live at the moment as per the query. its more agentic. for example these graphs were generated on the go to provide a strong support to the research query. there are other things too - such as you can build games with it, and many other tasks which involves chain of different small tasks.

Фото профиля lambda

lambda1 год назад

@perplexity_ai is it better than o3?

Фото профиля Krishna Kaasyap

Krishna Kaasyap1 год назад

@perplexity_ai Is this the Perplexity's replica of @ManusAI_HQ??

Фото профиля (((Cazador-de-Chimba))) 🇦🇺

(((Cazador-de-Chimba))) 🇦🇺1 год назад

@perplexity_ai Cool so how much is the subscription? I need something. More agentic than deep research to plan my whole Brazilian self sufficient farm plan, to escape the 400 million deaths from bio engineered H5N1

Фото профиля Andrew Arkins

Andrew Arkins1 год назад

@perplexity_ai Any economists with decades of experience want to chime in here?

Похожие видео

I asked Perplexity Computer one question: “If Nvidia’s AI data center revenue doubles again, map exactly where every incremental dollar flows across the semiconductor supply chain with a chart” It generated this full supply chain chart and video in minutes. It shows exactly who benefits - memory, foundry, packaging, and more. This level of research used to take hours. Now it takes minutes.

I asked Perplexity Computer one question: “If Nvidia’s AI data center revenue doubles again, map exactly where every incremental dollar flows across the semiconductor supply chain with a chart” It generated this full supply chain chart and video in minutes. It shows exactly who benefits - memory, foundry, packaging, and more. This level of research used to take hours. Now it takes minutes.

Venu

101,207 просмотров • 5 месяцев назад

Perplexity just became the first AI company to truly go head-to-head with Palantir Using Perplexity Computer (with no local setup or single LLM limitation), it was able to build me a World Monitor with real-time data to analyze the world situation, flight situation, war situation, and many more... using skills and a combination of LLMs wherever they're best. I'm super impressed Aravind Srinivas

Perplexity just became the first AI company to truly go head-to-head with Palantir Using Perplexity Computer (with no local setup or single LLM limitation), it was able to build me a World Monitor with real-time data to analyze the world situation, flight situation, war situation, and many more... using skills and a combination of LLMs wherever they're best. I'm super impressed Aravind Srinivas

Rohit Ghumare

89,998 просмотров • 5 месяцев назад

"We don't do product reviews." In this clip, Aravind Srinivas (CEO Perplexity) shares how he empowers teams to ship faster by giving feedback as a user instead of as the CEO. Aravind gave me an inside look at how Perplexity builds products, including: • Perplexity's incredible shipping velocity • Their path to 100M+ queries and beyond • Search ads that are better than ten blue links I also love his honest advice for young people who want to build something great. 📌 Watch our full interview now:

"We don't do product reviews." In this clip, Aravind Srinivas (CEO Perplexity) shares how he empowers teams to ship faster by giving feedback as a user instead of as the CEO. Aravind gave me an inside look at how Perplexity builds products, including: • Perplexity's incredible shipping velocity • Their path to 100M+ queries and beyond • Search ads that are better than ten blue links I also love his honest advice for young people who want to build something great. 📌 Watch our full interview now:

Peter Yang

339,759 просмотров • 1 год назад

Just wrapped an amazing panel with House of ZK. ZK used to be a PhD-only club. Now, with zkVMs, any dev can build with it. We're solving the performance vs. programmability trade-off so that in 5-10 years, 99% of dApps can run on verifiable off-chain compute. The future is off-chain, verified on-chain. Thanks for having us House of ZK!

Just wrapped an amazing panel with House of ZK. ZK used to be a PhD-only club. Now, with zkVMs, any dev can build with it. We're solving the performance vs. programmability trade-off so that in 5-10 years, 99% of dApps can run on verifiable off-chain compute. The future is off-chain, verified on-chain. Thanks for having us House of ZK!

Brevis

32,095 просмотров • 10 месяцев назад

Perplexity co-founder and CEO Aravind Srinivas (Aravind Srinivas) on the race to build the AI browser of the future. At AI Startup School in San Francisco. 00:48 - Perplexity's Current Status and Challenges 01:16 - Future Plans: The Browser Bet 03:18 - Competition and Market Dynamics 04:43 - The Importance of Speed and Innovation 05:51 - Founding Perplexity: The Early Days 09:18 - Product Evolution and User Experience 19:44 - Running the Company and Future Outlook 20:15 - AI Tools in Software Engineering 20:31 - Adoption and Implementation of AI Coding Tools 21:11 - Challenges and Benefits of AI in Development 22:35 - Brand Value and Competition 23:56 - Network Effects and Integrations 27:40 - Business Model and Revenue Streams 29:54 - Advice for Founders 31:33 - Audience Q&A

Y Combinator

236,501 просмотров • 1 год назад

Here's my conversation with Aravind Srinivas (Aravind Srinivas), CEO of Perplexity. We talk about the history & future of AI, web search, and the Internet. Plus, lots of great advice on how to start and run a company. I met Aravind many years ago at Berkeley, and it was a bit surreal to sit down now and talk about the amazing progress in AI that happened since then. This was a fun and fascinating conversation. It's here on X in full, and is up on YouTube, Spotify, and everywhere else. Links in comment. Timestamps: 0:00 - Introduction 1:53 - How Perplexity works 9:50 - How Google works 32:17 - Larry Page and Sergey Brin 46:52 - Jeff Bezos 50:20 - Elon Musk 52:38 - Jensen Huang 55:55 - Mark Zuckerberg 57:23 - Yann LeCun 1:04:09 - Breakthroughs in AI 1:20:07 - Curiosity 1:26:24 - $1 trillion dollar question 1:41:14 - Perplexity origin story 1:56:27 - RAG 2:18:45 - 1 million H100 GPUs 2:21:17 - Advice for startups 2:33:54 - Future of search

Here's my conversation with Aravind Srinivas (Aravind Srinivas), CEO of Perplexity. We talk about the history & future of AI, web search, and the Internet. Plus, lots of great advice on how to start and run a company. I met Aravind many years ago at Berkeley, and it was a bit surreal to sit down now and talk about the amazing progress in AI that happened since then. This was a fun and fascinating conversation. It's here on X in full, and is up on YouTube, Spotify, and everywhere else. Links in comment. Timestamps: 0:00 - Introduction 1:53 - How Perplexity works 9:50 - How Google works 32:17 - Larry Page and Sergey Brin 46:52 - Jeff Bezos 50:20 - Elon Musk 52:38 - Jensen Huang 55:55 - Mark Zuckerberg 57:23 - Yann LeCun 1:04:09 - Breakthroughs in AI 1:20:07 - Curiosity 1:26:24 - $1 trillion dollar question 1:41:14 - Perplexity origin story 1:56:27 - RAG 2:18:45 - 1 million H100 GPUs 2:21:17 - Advice for startups 2:33:54 - Future of search

Lex Fridman

703,701 просмотров • 2 лет назад

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,403 просмотров • 2 лет назад

Through the decades I would find locations like this to Save Wisdom. No matter how many times I would do this, you never get used to the ghosts you feel haunting these halls. The life of those folks that built these places. The hardest one to deal with was Bell Labs.

Through the decades I would find locations like this to Save Wisdom. No matter how many times I would do this, you never get used to the ghosts you feel haunting these halls. The life of those folks that built these places. The hardest one to deal with was Bell Labs.

Brian Roemmele

30,848 просмотров • 1 год назад

🚨🇮🇷🇺🇸 THE STATE DEPARTMENT'S OWN DATA CONTRADICTS THE NARRATIVE IT USED TO JUSTIFY ESCALATION WITH IRAN Larry Johnson says the "world's number one sponsor of terrorism" label pinned on Iran was built on a fundamental misreading of the region. The vast majority of international attacks came from radical Sunni groups, not Shia entities tied to Tehran. Decades of policy built on a distortion. And now it's being used to justify a war. Deep dive with Larry Johnson below

🚨🇮🇷🇺🇸 THE STATE DEPARTMENT'S OWN DATA CONTRADICTS THE NARRATIVE IT USED TO JUSTIFY ESCALATION WITH IRAN Larry Johnson says the "world's number one sponsor of terrorism" label pinned on Iran was built on a fundamental misreading of the region. The vast majority of international attacks came from radical Sunni groups, not Shia entities tied to Tehran. Decades of policy built on a distortion. And now it's being used to justify a war. Deep dive with Larry Johnson below

Mario Nawfal

49,532 просмотров • 5 месяцев назад

Here's how I would learn data engineering basics in 2025: - Find a data source you care about (examples: gaming APIs, stock market, web scraping, etc) - Use Python to interact and ingest your source. Initially just write the data to a CSV. - Setup an account with Snowflake or Google BigQuery. - update your Python script to load a table in Snowflake/BigQuery - schedule your script with CRON in the cloud with a service like Heroku. - build aggregations and visualizations on top of your ingested data Only thing this misses is data quality and complex job orchestration which you can learn later! How would you learn data engineering nowadays?

Here's how I would learn data engineering basics in 2025: - Find a data source you care about (examples: gaming APIs, stock market, web scraping, etc) - Use Python to interact and ingest your source. Initially just write the data to a CSV. - Setup an account with Snowflake or Google BigQuery. - update your Python script to load a table in Snowflake/BigQuery - schedule your script with CRON in the cloud with a service like Heroku. - build aggregations and visualizations on top of your ingested data Only thing this misses is data quality and complex job orchestration which you can learn later! How would you learn data engineering nowadays?

Zach Wilson

20,368 просмотров • 1 год назад

I built a bot to trade faster than any human > found markets to bet which word Trump says in speech > used Deepgram Nova-3 to transcribe live speeches in matched words with markets > instantly sweep all orders under 99¢ > exit at $1.00 for profit > in the right hands, generates 6-figures/month All done in 2 hours 34 minutes using Perplexity, Opus 4.6, and a bit of brain None of my CS knowledge was used except deploying it on a server

I built a bot to trade faster than any human > found markets to bet which word Trump says in speech > used Deepgram Nova-3 to transcribe live speeches in matched words with markets > instantly sweep all orders under 99¢ > exit at $1.00 for profit > in the right hands, generates 6-figures/month All done in 2 hours 34 minutes using Perplexity, Opus 4.6, and a bit of brain None of my CS knowledge was used except deploying it on a server

Rossium

103,532 просмотров • 5 месяцев назад

A Wisconsin NGO named Newcap got $14 million dollars in one year from taxpayers to serve low income Americans with housing assistance They instead used the money for Executive pay increases and throw expensive conferences They falsified how the money was spent on reports “A former new CAP employee with decades of construction experience tells Fox when it was time to provide those reports. Leadership would gather in a room and often come up with numbers. Seemingly out of nowhere”

A Wisconsin NGO named Newcap got $14 million dollars in one year from taxpayers to serve low income Americans with housing assistance They instead used the money for Executive pay increases and throw expensive conferences They falsified how the money was spent on reports “A former new CAP employee with decades of construction experience tells Fox when it was time to provide those reports. Leadership would gather in a room and often come up with numbers. Seemingly out of nowhere”

Wall Street Apes

48,595 просмотров • 5 месяцев назад

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Santiago

126,434 просмотров • 10 месяцев назад

Jupyter Agents - LLMs running data analysis directly in a notebook! The agent can load data, execute code, plot results and following your guidance and ideas! A very natural way to collaborate with an LLM over data and it's just scratching the surface of what's possible soon!

Jupyter Agents - LLMs running data analysis directly in a notebook! The agent can load data, execute code, plot results and following your guidance and ideas! A very natural way to collaborate with an LLM over data and it's just scratching the surface of what's possible soon!

Leandro von Werra

200,291 просмотров • 1 год назад

Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to and log in 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. E.g., generate graphs for exploratory data analysis. 5. Liner will generate a variety of graphs for you. 6. It also generates an insightful data analysis report. ✦ You can edit the report. For example, you can: ✦ Insert citations in the report ✦ Make changes to the text ✦ Add/remove any graphs After making changes, you can download the report. Try Liner today. It’s FREE. Liner link:

Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to and log in 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. E.g., generate graphs for exploratory data analysis. 5. Liner will generate a variety of graphs for you. 6. It also generates an insightful data analysis report. ✦ You can edit the report. For example, you can: ✦ Insert citations in the report ✦ Make changes to the text ✦ Add/remove any graphs After making changes, you can download the report. Try Liner today. It’s FREE. Liner link:

Faheem Ullah

11,974 просмотров • 4 месяцев назад

🚨 Warsh just dropped his real agenda: a full Fed overhaul. Task forces forming on communications, balance sheet, data sources, jobs/AI productivity, and the inflation framework itself. This isn't a one-meeting hawkish blip it's a structural rewrite of how the Fed operates. 👀 Crypto should care more about this than the dot plot. $BTC $XRP $ETH

🚨 Warsh just dropped his real agenda: a full Fed overhaul. Task forces forming on communications, balance sheet, data sources, jobs/AI productivity, and the inflation framework itself. This isn't a one-meeting hawkish blip it's a structural rewrite of how the Fed operates. 👀 Crypto should care more about this than the dot plot. $BTC $XRP $ETH

Xaif Crypto

64,535 просмотров • 2 месяцев назад

Andrew Ng just released a 1-hour course on building agentic knowledge Graphs from scratch: • 00:00 - Introduction to agentic knowledge Graphs • 03:07 - Construction of agentic Graphs • 14:00 - Architecture of multi-agent systems • 23:00 - Building agentic graphs with Google ADK • 01:06:03 - Why Graphsare the future of agentic AI Worth more than 10 articles on loop engineering. Watch it today, then read how to become a graph engineer in the article below.

Andrew Ng just released a 1-hour course on building agentic knowledge Graphs from scratch: • 00:00 - Introduction to agentic knowledge Graphs • 03:07 - Construction of agentic Graphs • 14:00 - Architecture of multi-agent systems • 23:00 - Building agentic graphs with Google ADK • 01:06:03 - Why Graphsare the future of agentic AI Worth more than 10 articles on loop engineering. Watch it today, then read how to become a graph engineer in the article below.

Codez

464,409 просмотров • 1 месяц назад