Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing "gap analysis"—new addition to scira's "extreme" mode! how it works—after the research plan is executed—the LLM will run a gap analysis to find the gaps in the results of the research plan and then search for the gaps and fill the information—and finally run a final synthesis or... show more

Scira AI

2,659 subscribers

15,428 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

3 Comments

Scira AI1 year ago

try here

Scira AI1 year ago

repo

Nigam Arora1 year ago

HOW MUCH WEALTH COULD YOU GENERATE IF YOU COULD FOLLOW THE MOST ACCURATE STOCK MARKET ANALYSIS? Over 100 million page views of Arora Calls. Unique proven ZYX method.

Related Videos

Every Prompt Can Do Research On ChatLLM!! We have hooked up GPT-4o with many tools, including doc generation, web scraping, and web search, and made it a lot more agentic in nature... If you ask it to scrape two URLs, digest the information, and perform a competitive analysis, it can do it in seconds! Notice the difference between ChatLLM and the $200 ChatGPT for the same prompt! It's very cool. The research is not quite deep yet; a dedicated agent who can do that will arrive next week. In the meantime, have fun with shallow research 😂.

Every Prompt Can Do Research On ChatLLM!! We have hooked up GPT-4o with many tools, including doc generation, web scraping, and web search, and made it a lot more agentic in nature... If you ask it to scrape two URLs, digest the information, and perform a competitive analysis, it can do it in seconds! Notice the difference between ChatLLM and the $200 ChatGPT for the same prompt! It's very cool. The research is not quite deep yet; a dedicated agent who can do that will arrive next week. In the meantime, have fun with shallow research 😂.

Bindu Reddy

12,802 views • 1 year ago

Today, Search Live is available in English in the U.S. — no Labs opt-in required. ✨ You can now have a free-flowing, back-and-forth conversation with Search using your voice and phone camera. Live in Search combines the power of Google Lens and AI Mode to see and accurately identify objects in front of you. This allows Search to understand exactly what you are looking at and help you find the most relevant information across the web to respond to your questions in real time. Try it today by tapping Live in the Google app (iOS and Android) or Lens, and let us know what you think!

Today, Search Live is available in English in the U.S. — no Labs opt-in required. ✨ You can now have a free-flowing, back-and-forth conversation with Search using your voice and phone camera. Live in Search combines the power of Google Lens and AI Mode to see and accurately identify objects in front of you. This allows Search to understand exactly what you are looking at and help you find the most relevant information across the web to respond to your questions in real time. Try it today by tapping Live in the Google app (iOS and Android) or Lens, and let us know what you think!

Google AI

48,572 views • 8 months ago

PhD Students – How to identify a research gap in seconds? Use this FREE tool to identify research gap in seconds. 1. Go to 2. Click on 𝑇𝑜𝑝𝑖𝑐 𝐸𝑥𝑝𝑙𝑜𝑟𝑒𝑟 ---> 𝐶𝑟𝑒𝑎𝑡𝑖𝑣𝑒 𝑇𝑜𝑜𝑙 3. Enter your topic e.g., deep learning for healthcare 4. Now click on 𝑔𝑒𝑛𝑒𝑟𝑎𝑡𝑒 𝑖𝑑𝑒𝑎𝑠 5. ResearchCollab will give you the following 7 gaps ➝ Research that combines multiple existing research ➝ Research that adapts a new approach/technology ➝ Research that modifies existing variables in research ➝ Research that incorporates new variables ➝ Research that eliminates variables from research ➝ Research that re-arrange existing variables Pick the gap you think has the most potential. Then click on 𝑡𝑜𝑝𝑖𝑐 𝑎𝑛𝑎𝑙𝑦𝑠𝑖𝑠 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐂𝐨𝐥𝐥𝐚𝐛 will dive deeper into the selected topic It gives you different angles of the chosen research gap. It is very helpful and at the same time very easy to use Try 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐂𝐨𝐥𝐥𝐚𝐛 today:

PhD Students – How to identify a research gap in seconds? Use this FREE tool to identify research gap in seconds. 1. Go to 2. Click on 𝑇𝑜𝑝𝑖𝑐 𝐸𝑥𝑝𝑙𝑜𝑟𝑒𝑟 ---> 𝐶𝑟𝑒𝑎𝑡𝑖𝑣𝑒 𝑇𝑜𝑜𝑙 3. Enter your topic e.g., deep learning for healthcare 4. Now click on 𝑔𝑒𝑛𝑒𝑟𝑎𝑡𝑒 𝑖𝑑𝑒𝑎𝑠 5. ResearchCollab will give you the following 7 gaps ➝ Research that combines multiple existing research ➝ Research that adapts a new approach/technology ➝ Research that modifies existing variables in research ➝ Research that incorporates new variables ➝ Research that eliminates variables from research ➝ Research that re-arrange existing variables Pick the gap you think has the most potential. Then click on 𝑡𝑜𝑝𝑖𝑐 𝑎𝑛𝑎𝑙𝑦𝑠𝑖𝑠 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐂𝐨𝐥𝐥𝐚𝐛 will dive deeper into the selected topic It gives you different angles of the chosen research gap. It is very helpful and at the same time very easy to use Try 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐂𝐨𝐥𝐥𝐚𝐛 today:

Faheem Ullah

105,061 views • 2 months ago

Web search is now enabled by default for the Codex CLI and IDE Extension 🎉 By default it will use a web search cache but you can toggle live results or if you use --yolo live results are enabled by default. More details in the changelog 👇

Web search is now enabled by default for the Codex CLI and IDE Extension 🎉 By default it will use a web search cache but you can toggle live results or if you use --yolo live results are enabled by default. More details in the changelog 👇

dominik kundel

265,718 views • 4 months ago

You can create a Grok Project, have it search for relevant research papers, and attach the good ones to your project. Because Grok 4 can parse PDFs, you can interact with the model, and it will have direct knowledge of your research.

You can create a Grok Project, have it search for relevant research papers, and attach the good ones to your project. Because Grok 4 can parse PDFs, you can interact with the model, and it will have direct knowledge of your research.

tetsuo

1,662,674 views • 8 months ago

Just made an MCP server to use Anthropic’s new web search tool. What I love about it is that the search is agentic. You can use any model to call a Claude instance that returns processed search results. Or specify how deep the search should be. 🔗 Link in the comments.

Just made an MCP server to use Anthropic’s new web search tool. What I love about it is that the search is agentic. You can use any model to call a Claude instance that returns processed search results. Or specify how deep the search should be. 🔗 Link in the comments.

Pietro Schirano

29,189 views • 1 year ago

The upgraded Google app for desktop is now available for Windows users globally in English. 💻✨ Use a simple keyboard shortcut (Alt + Space) to instantly find what you need—information from the web, your computer files, installed apps, and Google Drive files—all from the Search box. With AI Mode in Search and Lens built right in, you can ask whatever’s on your mind or search what’s on your screen to get helpful AI-powered responses with links to the web.

The upgraded Google app for desktop is now available for Windows users globally in English. 💻✨ Use a simple keyboard shortcut (Alt + Space) to instantly find what you need—information from the web, your computer files, installed apps, and Google Drive files—all from the Search box. With AI Mode in Search and Lens built right in, you can ask whatever’s on your mind or search what’s on your screen to get helpful AI-powered responses with links to the web.

Rajan Patel

113,904 views • 1 month ago

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

👋 Jan

689,722 views • 9 months ago

New in Claude Code: /ultraplan Claude builds an implementation plan for you on the web. You can read it and edit it, then run the plan on the web or back in your terminal. Available now in preview for all users with CC on the web enabled.

New in Claude Code: /ultraplan Claude builds an implementation plan for you on the web. You can read it and edit it, then run the plan on the web or back in your terminal. Available now in preview for all users with CC on the web enabled.

Thariq

1,295,895 views • 1 month ago

📍A local SEO trick every pro should know: Use the UULE parameter to set a precise location for your search results. Adding a UULE parameter to your Google search query lets you see search results from a specific region without needing an extension or being physically there. Here’s how: 1️⃣ Generate a UULE for the location (Find a tool by googling “uule generator”) You will get a code that looks like this: &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ 2️⃣ Now run any search in Google. 3️⃣ Look at the URL for your search and replace the last part of it with the UULE parameter. For example: google . com/search?q=sushi+restaurant &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ How do you set your search location? #seo #localseo

📍A local SEO trick every pro should know: Use the UULE parameter to set a precise location for your search results. Adding a UULE parameter to your Google search query lets you see search results from a specific region without needing an extension or being physically there. Here’s how: 1️⃣ Generate a UULE for the location (Find a tool by googling “uule generator”) You will get a code that looks like this: &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ 2️⃣ Now run any search in Google. 3️⃣ Look at the URL for your search and replace the last part of it with the UULE parameter. For example: google . com/search?q=sushi+restaurant &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ How do you set your search location? #seo #localseo

Darren Shaw

28,502 views • 2 years ago

Introducing /search - the simplest way for agents and devs to discover the web 👀 Our #1 most requested endpoint is finally here. Search the web AND scrape all results in an LLM-ready format with one API call. Now live on our API, MCP, and all integrations 🔥

Introducing /search - the simplest way for agents and devs to discover the web 👀 Our #1 most requested endpoint is finally here. Search the web AND scrape all results in an LLM-ready format with one API call. Now live on our API, MCP, and all integrations 🔥

Firecrawl

390,772 views • 1 year ago

You can now perform web searches AND scrape their full content in AI code editors. Simply add the new Firecrawl Search MCP, and it will search the web and get all the page contents for each result in one operation. Here’s how:

You can now perform web searches AND scrape their full content in AI code editors. Simply add the new Firecrawl Search MCP, and it will search the web and get all the page contents for each result in one operation. Here’s how:

Alvaro Cintas

43,424 views • 1 year ago

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

Isaac Flath

40,212 views • 1 month ago

FireCrawl just launched Fire Enrich. You can now upload a CSV with emails, and the AI agents will search the web to automatically fill in any missing data you need. Here’s how:

FireCrawl just launched Fire Enrich. You can now upload a CSV with emails, and the AI agents will search the web to automatically fill in any missing data you need. Here’s how:

Alvaro Cintas

34,568 views • 11 months ago

You can now connect GitHub repos to deep research in ChatGPT. 🐙 Ask a question and the deep research agent will read and search the repo’s source code and PRs, returning a detailed report with citations. Hit deep research → GitHub to get started.

You can now connect GitHub repos to deep research in ChatGPT. 🐙 Ask a question and the deep research agent will read and search the repo’s source code and PRs, returning a detailed report with citations. Hit deep research → GitHub to get started.

OpenAI Developers

1,505,525 views • 1 year ago

YC F24's @AdittoCo lets you run search engine marketing without marketers. Aditto generates new search ads and custom landing pages daily and lets you launch them with the click of a button. Congrats on the launch, Will Jack and Keller Maloney!

YC F24's @AdittoCo lets you run search engine marketing without marketers. Aditto generates new search ads and custom landing pages daily and lets you launch them with the click of a button. Congrats on the launch, Will Jack and Keller Maloney!

Y Combinator

26,692 views • 1 year ago

Update: The new features rollout this week A Google spokesperson responded to the TechCrunch article: “We’re continuing to display blue links on the search results page in addition to AI responses. If someone chooses to ask a follow-up from an AI Overview, or selects the AI Mode button in the Search box, then that takes them to AI Mode. It doesn’t happen automatically – people have to choose to navigate to AI Mode" (via philip lewis)

Update: The new features rollout this week A Google spokesperson responded to the TechCrunch article: “We’re continuing to display blue links on the search results page in addition to AI responses. If someone chooses to ask a follow-up from an AI Overview, or selects the AI Mode button in the Search box, then that takes them to AI Mode. It doesn’t happen automatically – people have to choose to navigate to AI Mode" (via philip lewis)

Culture Crave 🍿

159,193 views • 14 days ago

④ How to find these sneaky insiders? ➬ First, visit: ➬ Look for trending tokens in the past 6h or 24h ➬ Click on the Top Traders section ➬ Search for early trades ➬ Copy the wallet address ➬ Next, go to: AlphaTrace(🔎,💪🏻) ➬ For a better results, you can filter the wallets you will find by $500k+ PNL and a 60% win rate

④ How to find these sneaky insiders? ➬ First, visit: ➬ Look for trending tokens in the past 6h or 24h ➬ Click on the Top Traders section ➬ Search for early trades ➬ Copy the wallet address ➬ Next, go to: AlphaTrace(🔎,💪🏻) ➬ For a better results, you can filter the wallets you will find by $500k+ PNL and a 60% win rate

ardizor 🧙‍♂️

32,944 views • 2 years ago

I’ve built the Perplexity of the DarkWeb! Let me explain 👇 First, if you've been living in a cave, Perplexity is a search engine powered by LLMs. So what if we could do the same for the darkweb? Compared to the clear web, browsing the darkweb requires a few things: - A Tor connection (easy) ✅ - A search engine you can query (for the demo, I’m using Ahmia) ✅ - A list of curated onion websites (especially useful for threat intel or sites not indexed by Ahmia) ✅ Now here are the limitations: - Many underground forums and websites require login access, or captcha. - Ahmia works, but it's limited, you can combine it with other search engines. - Be careful when scraping, sometimes you get more than what you search for. This is one of the cool projects you will learn in my training at the upcoming Blackhat USA and /ˈziːf-kɒn/ 👇 ➡️ ➡️

I’ve built the Perplexity of the DarkWeb! Let me explain 👇 First, if you've been living in a cave, Perplexity is a search engine powered by LLMs. So what if we could do the same for the darkweb? Compared to the clear web, browsing the darkweb requires a few things: - A Tor connection (easy) ✅ - A search engine you can query (for the demo, I’m using Ahmia) ✅ - A list of curated onion websites (especially useful for threat intel or sites not indexed by Ahmia) ✅ Now here are the limitations: - Many underground forums and websites require login access, or captcha. - Ahmia works, but it's limited, you can combine it with other search engines. - Be careful when scraping, sometimes you get more than what you search for. This is one of the cool projects you will learn in my training at the upcoming Blackhat USA and /ˈziːf-kɒn/ 👇 ➡️ ➡️

Thomas Roccia 🤘

42,420 views • 1 year ago

Why search some of the Internet, when you can search all of the Internet? All the Internet was created to be extremely fast, easy to use, secure and have the most relevant search results. You can search the whole Internet with All the Internet.

Why search some of the Internet, when you can search all of the Internet? All the Internet was created to be extremely fast, easy to use, secure and have the most relevant search results. You can search the whole Internet with All the Internet.

All the Internet

4,902,925 views • 1 year ago