正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Perplexity Computer uses Excel like a real financial analyst. We gave Computer Amazon's last 5 earnings releases. It built us a fully working 3-statement financial model with an assumptions tab, charts, and clean formatting that would impress your MD.

Computer

387,804 subscribers

83,052 次观看 • 8 个月前 •via X (Twitter)

教育科学技术财经

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

No more manually pulling data. We gave Perplexity Computer a simple prompt and a free Federal Reserve API key. Minutes later: a fully formatted Excel spreadsheet with live macro indicators and charts.

No more manually pulling data. We gave Perplexity Computer a simple prompt and a free Federal Reserve API key. Minutes later: a fully formatted Excel spreadsheet with live macro indicators and charts.

Computer

105,606 次观看 • 8 个月前

You can now embed your connectors directly inside web apps built by Perplexity Computer. To demonstrate, we built a document editor that uses the Google Docs and Notion connectors to fetch, edit, and save docs across both.

You can now embed your connectors directly inside web apps built by Perplexity Computer. To demonstrate, we built a document editor that uses the Google Docs and Notion connectors to fetch, edit, and save docs across both.

Computer

34,101 次观看 • 8 个月前

I’m really proud of this launch. We just shipped an Earnings Feed that updates ~2 seconds after earnings go live. It gives you every reported financial through a clean, structured API. Available to all today.

I’m really proud of this launch. We just shipped an Earnings Feed that updates ~2 seconds after earnings go live. It gives you every reported financial through a clean, structured API. Available to all today.

Virat Singh

49,818 次观看 • 6 个月前

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity

534,569 次观看 • 8 个月前

Perplexity Computer

Perplexity Computer

Tatiana Tsiguleva

32,821 次观看 • 8 个月前

We are WisdomTree, a global financial innovator. We empower investors and financial professionals with cost-efficient and performance-driven ETFs and ETPs. Join us and shape your future.

We are WisdomTree, a global financial innovator. We empower investors and financial professionals with cost-efficient and performance-driven ETFs and ETPs. Join us and shape your future.

WisdomTree, Inc.

6,781,037 次观看 • 3 年前

No one’s pulled this off yet. A stock market API that updates the moment earnings drop. I’ve built this for months. It’s almost ready. Yesterday I tested it on $ABNB. The Q2 2025 income statement hit our API 3 seconds after release. Data was clean. Structured. Accurate. Launching soon on Financial Datasets.

No one’s pulled this off yet. A stock market API that updates the moment earnings drop. I’ve built this for months. It’s almost ready. Yesterday I tested it on $ABNB. The Q2 2025 income statement hit our API 3 seconds after release. Data was clean. Structured. Accurate. Launching soon on Financial Datasets.

virat

13,658 次观看 • 1 年前

streamer's computer accidentally opens a tab

streamer's computer accidentally opens a tab

Paladin

1,714,727 次观看 • 8 个月前

imagine a personal agent that controls your mac from anywhere. chat with it on iOS, web, text, even email. it takes action on your computer. and it has a computer of its own – a cloud server, where you can host, automate, and do all kinds of work. coming soon on Zo Computer

imagine a personal agent that controls your mac from anywhere. chat with it on iOS, web, text, even email. it takes action on your computer. and it has a computer of its own – a cloud server, where you can host, automate, and do all kinds of work. coming soon on Zo Computer

ben guo 🪽

15,071 次观看 • 10 个月前

Automate ETL over Financial Data 📊 Most real-world financials are not “database-shaped”, and requires a ton of human effort to manipulate/copy an Excel sheet into structured formats for analysis. We recently launched LlamaSheets - a specialized AI agent that automatically structures your Excel spreadsheet into a 2D format for analysis. There are so many use cases for Excel, and accounting is a huge subcategory here. Check it out:

Automate ETL over Financial Data 📊 Most real-world financials are not “database-shaped”, and requires a ton of human effort to manipulate/copy an Excel sheet into structured formats for analysis. We recently launched LlamaSheets - a specialized AI agent that automatically structures your Excel spreadsheet into a 2D format for analysis. There are so many use cases for Excel, and accounting is a huge subcategory here. Check it out:

Jerry Liu

21,354 次观看 • 11 个月前

I built more 3-statement models by hand at Morgan Stanley than I'd like to admit. Claude in Excel is a game changer .... here's how I build any model in 5 passes: The process is all about context window management to minimize hardcodes + hallucinations and maximize control over model style. (1) Gather the sources. Filings, earnings transcripts, raw financials and any model or template I already have. I have it make a clean folder I point Claude to. (2) Turn the sources into a JSON or .md input. A short inputs file with historicals, segment KPIs, accounting definitions and operating drivers. This step converts many megabites of PDF's into a liteweight doc for RAG. (3) Build the structure (in your firm style). Building the shell lets you reverse engineer your firm model style .... which Claude will never have context for. (4) Add the forecast. I take the same historicals JSON or .md and run a deep research workflow to fill in those parameters but for forward assumptions. Obviously with sources so I can check assumptions. Then I layer in that file to project out forward assumptions. (5) Audit it in a fresh chat. New chat is necessary to hard reset the context window (improves quality). A simple prompt even to check for hard + soft errors can rank issues by severity (eg broken formulas and things that don't tie to assumptions that look off) If you're really advanced at Claude Code - you can wrap this into a programmatic skill package in your firm build style .... maybe I write a thread about that next time. In the meantime, I've put together this AI for Excel build guide here:

I built more 3-statement models by hand at Morgan Stanley than I'd like to admit. Claude in Excel is a game changer .... here's how I build any model in 5 passes: The process is all about context window management to minimize hardcodes + hallucinations and maximize control over model style. (1) Gather the sources. Filings, earnings transcripts, raw financials and any model or template I already have. I have it make a clean folder I point Claude to. (2) Turn the sources into a JSON or .md input. A short inputs file with historicals, segment KPIs, accounting definitions and operating drivers. This step converts many megabites of PDF's into a liteweight doc for RAG. (3) Build the structure (in your firm style). Building the shell lets you reverse engineer your firm model style .... which Claude will never have context for. (4) Add the forecast. I take the same historicals JSON or .md and run a deep research workflow to fill in those parameters but for forward assumptions. Obviously with sources so I can check assumptions. Then I layer in that file to project out forward assumptions. (5) Audit it in a fresh chat. New chat is necessary to hard reset the context window (improves quality). A simple prompt even to check for hard + soft errors can rank issues by severity (eg broken formulas and things that don't tie to assumptions that look off) If you're really advanced at Claude Code - you can wrap this into a programmatic skill package in your firm build style .... maybe I write a thread about that next time. In the meantime, I've put together this AI for Excel build guide here:

Dave Wang

52,852 次观看 • 11 天前

Grok for Excel is live. Use Grok 4.5 to build financial models, analyze market data, and generate charts and graphs. Try it now

Grok for Excel is live. Use Grok 4.5 to build financial models, analyze market data, and generate charts and graphs. Try it now

Grok

24,310,772 次观看 • 3 个月前

🚨BREAKING: China just released an AI employee that runs on your own computer. It can search the web, write code, build websites, make slides, and create videos. All by itself. It even comes with its own built-in computer. 100% Open Source.

🚨BREAKING: China just released an AI employee that runs on your own computer. It can search the web, write code, build websites, make slides, and create videos. All by itself. It even comes with its own built-in computer. 100% Open Source.

Hasan Toor

20,679 次观看 • 7 个月前

$SUPERNOVA IS LIVE AND DELIVERED! After all these years, and all the work that went into it, I almost can’t believe I can finally say this out loud, *Supernova is fully live.* (Bears repeating every single day for the next 30 days, and just taking it in) And with it, we introduced the Finance Computer. A bold, categorically different, and remarkably simple product. Built on a radical idea: brands, businesses, agents, and robots don’t want more financial complexity. They simply want a better way to access, move, and program money. One connection. Financial superpowers. This is a B2B and B2M product. And the simpler we can make it, the more powerful it becomes. At first, this may feel like a narrative violation to some people in crypto, but then an important realization comes. This product is not built for crypto people. It is built to strike a chord with the real world. Businesses that want money to move instantly. Brands that want financial capabilities embedded directly into their products. Agents and robots that need to transact on their own. All through one simple interface. Regulated. Secure. Global. A new category of machine-ready finance is here, now. Money, capital, assets, and markets moving around the world in a fraction of a second. Open and live 24/7. Programmable by default. Gradually, becoming accessible to anyone, anywhere. This is what the Finance Computer makes possible.$

SUPERNOVA IS LIVE AND DELIVERED! After all these years, and all the work that went into it, I almost can’t believe I can finally say this out loud, Supernova is fully live. (Bears repeating every single day for the next 30 days, and just taking it in) And with it, we introduced the Finance Computer. A bold, categorically different, and remarkably simple product. Built on a radical idea: brands, businesses, agents, and robots don’t want more financial complexity. They simply want a better way to access, move, and program money. One connection. Financial superpowers. This is a B2B and B2M product. And the simpler we can make it, the more powerful it becomes. At first, this may feel like a narrative violation to some people in crypto, but then an important realization comes. This product is not built for crypto people. It is built to strike a chord with the real world. Businesses that want money to move instantly. Brands that want financial capabilities embedded directly into their products. Agents and robots that need to transact on their own. All through one simple interface. Regulated. Secure. Global. A new category of machine-ready finance is here, now. Money, capital, assets, and markets moving around the world in a fraction of a second. Open and live 24/7. Programmable by default. Gradually, becoming accessible to anyone, anywhere. This is what the Finance Computer makes possible.

Beniamin Mincu |🇺🇸/acc

37,219 次观看 • 1 个月前

Big change in Dexter today. We replaced 20+ financial tools with a single Financial Search sub-agent. It’s web search, but for financial data. Dexter can search across: • earnings • SEC filings • stock prices • news + more Bonus: it’s fully extensible. Add crypto, options, or any data you need.

Big change in Dexter today. We replaced 20+ financial tools with a single Financial Search sub-agent. It’s web search, but for financial data. Dexter can search across: • earnings • SEC filings • stock prices • news + more Bonus: it’s fully extensible. Add crypto, options, or any data you need.

virat

24,561 次观看 • 10 个月前

We asked Seedance 2.5 for a quiz show. One prompt gave us the studio, the host, the contestant, and a million-dollar question we would not have dared to write ourselves. Generated on 0G Private Computer.

We asked Seedance 2.5 for a quiz show. One prompt gave us the studio, the host, the contestant, and a million-dollar question we would not have dared to write ourselves. Generated on 0G Private Computer.

0G Labs

21,140 次观看 • 2 个月前

these 2 FREE GitHub repos should honestly be illegal in trading... REA + Kronos + Claude Code can turn a regular computer into a Bloomberg-style market research terminal hedge funds spend thousands on market data and research tools, while these 2 open-source projects give you the building blocks to create your own system here's how it works: REA lets AI agents understand how software works and reconstruct its functionality Kronos treats financial candles like tokens and predicts possible future price movements combine them and you get a financial terminal where charts can display AI-generated forecasts here's how to build it yourself for FREE: step 1 → connect REA to Claude Code using and map out a professional market terminal: quotes, charts, screeners, news and market dashboards step 2 → ask Claude to build the complete interface with equities, FX, commodities, crypto, global indices and financial news step 3 → connect public market data APIs to populate the terminal with prices, charts and market information step 4 → clone and load Kronos-small, the 24.7M parameter financial forecasting model step 5 → feed Kronos the last 512 candles and generate predictions for the next 24, similar to how an LLM predicts the next tokens step 6 → sample 100 possible future price paths and display them directly on the terminal charts step 7 → analyze the forecast distribution, identify market regimes and backtest the strategies with realistic fees before using real capital the result: a Bloomberg-style research terminal combining market data, charts, financial news and AI-powered probabilistic forecasting in one workspace i won't say anything more... bookmark this and thank me later ↓

these 2 FREE GitHub repos should honestly be illegal in trading... REA + Kronos + Claude Code can turn a regular computer into a Bloomberg-style market research terminal hedge funds spend thousands on market data and research tools, while these 2 open-source projects give you the building blocks to create your own system here's how it works: REA lets AI agents understand how software works and reconstruct its functionality Kronos treats financial candles like tokens and predicts possible future price movements combine them and you get a financial terminal where charts can display AI-generated forecasts here's how to build it yourself for FREE: step 1 → connect REA to Claude Code using and map out a professional market terminal: quotes, charts, screeners, news and market dashboards step 2 → ask Claude to build the complete interface with equities, FX, commodities, crypto, global indices and financial news step 3 → connect public market data APIs to populate the terminal with prices, charts and market information step 4 → clone and load Kronos-small, the 24.7M parameter financial forecasting model step 5 → feed Kronos the last 512 candles and generate predictions for the next 24, similar to how an LLM predicts the next tokens step 6 → sample 100 possible future price paths and display them directly on the terminal charts step 7 → analyze the forecast distribution, identify market regimes and backtest the strategies with realistic fees before using real capital the result: a Bloomberg-style research terminal combining market data, charts, financial news and AI-powered probabilistic forecasting in one workspace i won't say anything more... bookmark this and thank me later ↓

ludoonchart

21,089 次观看 • 23 天前

Computer use has gotten incredibly good in the past year, and it works great in Muse out of the box! Muse ships with a browser that it uses for tasks that it can't solve with an API or connector. At this point, it's hard to come up with tasks that computer use models aren't able to solve well, even when spanning into a 1hr+ time horizon (see the progress on OSWorld 2.0!) Here's a sped up version of it working for finding the cheapest flights from SF -> NYC!

Computer use has gotten incredibly good in the past year, and it works great in Muse out of the box! Muse ships with a browser that it uses for tasks that it can't solve with an API or connector. At this point, it's hard to come up with tasks that computer use models aren't able to solve well, even when spanning into a 1hr+ time horizon (see the progress on OSWorld 2.0!) Here's a sped up version of it working for finding the cheapest flights from SF -> NYC!

Matt Deitke

36,895 次观看 • 1 个月前

Any agent now has computer use in Superset with /computer Open any native app, click through it, and check the result. no screenshot-and-guess. built with Cua

Any agent now has computer use in Superset with /computer Open any native app, click through it, and check the result. no screenshot-and-guess. built with Cua

Kiet

10,876 次观看 • 2 个月前