Loading video...

Video Failed to Load

Go Home

📢 New Dataset Added to the Data-for-AI Campaign: EudraVigilance Database! We’ve added Europe’s largest public database of medicine side effects – EudraVigilance. It contains over 29.3M case reports, covering 16.9M unique ADR cases. Follow these steps to find valid links from the database: 1️⃣ Go to the EudraVigilance website....

super__protocol's profile picture

Super Protocol

25,072 subscribers

155,618 views • 1 year ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

3 Comments

Super Protocol's profile picture
Super Protocol1 year ago

👉 EudraVigilance website: 📃 Find our text guide here:

SecBriefs | Making Cybersecurity Simple's profile picture
SecBriefs | Making Cybersecurity Simple2 years ago

😔600+ healthcare data breaches exposed over 40 MILLION patient records last year. 💸The average cost of a healthcare data breach is $10.1 MILLION! 💔Protect your patients! Knowledge is power.💪 The "CYBERSECURITY DICTIONARY For Everyone" is on Amazon 🛒

NØCTIS | (🫰,✨)'s profile picture
NØCTIS | (🫰,✨)1 year ago

Let's hunt!

Related Videos

[VOTING] MTV VMAs 2024 HOW TO VOTE FOR SEVENTEEN AS VMAS BEST GROUP: 1. Go to MTV's IG Story, find the one with SEVENTEEN. 2. Click the link "🔗 VOTE FOR SEVENTEEN". 3. Once you are redirected to another site and you see "Thanks for voting!" your vote is counted. 4. Close the site then refresh MTV's Instagram page and repeat steps 1-4. Important note: Refreshing the page and stories will generate a new unique link, which is counted as one vote per unique click. So it is important to click directly from the Instagram Sotry as they will need the generated unique links from each clicks! #VoteSEVENTEEN_onVMAs #SEVENTEEN #세븐틴 #VMA 세븐틴(SEVENTEEN) Video Music Awards
0:45

[VOTING] MTV VMAs 2024 HOW TO VOTE FOR SEVENTEEN AS VMAS BEST GROUP: 1. Go to MTV's IG Story, find the one with SEVENTEEN. 2. Click the link "🔗 VOTE FOR SEVENTEEN". 3. Once you are redirected to another site and you see "Thanks for voting!" your vote is counted. 4. Close the site then refresh MTV's Instagram page and repeat steps 1-4. Important note: Refreshing the page and stories will generate a new unique link, which is counted as one vote per unique click. So it is important to click directly from the Instagram Sotry as they will need the generated unique links from each clicks! #VoteSEVENTEEN_onVMAs #SEVENTEEN #세븐틴 #VMA 세븐틴(SEVENTEEN) Video Music Awards

Worldwide Carats

180,877 views • 2 years ago

🚨 The $30,000 USDT Data-for-AI Campaign is LIVE on BNB Chain Featured activity series! Starting NOW, you can contribute high-quality, publicly available medical data links to build a decentralized and verifiable dataset for AI training. Why Join? 🔹 Earn Rewards: Share in $30,000 USDT + 1,000,000 Super Stakes. 🔹 Lead the Change: Verifiable input → Trusted AI. How to Participate: 1️⃣ Connect your wallet and register. 2️⃣ Claim your 300-point welcome bonus. 3️⃣ Submit links and climb the leaderboard. ✔️ Refer Friends: Get a 35% bonus for every valid link they submit! 👉 Watch the video guide below. 🔗 Start now: Let’s build the next generation of verifiable AI together
1:53

🚨 The $30,000 USDT Data-for-AI Campaign is LIVE on BNB Chain Featured activity series! Starting NOW, you can contribute high-quality, publicly available medical data links to build a decentralized and verifiable dataset for AI training. Why Join? 🔹 Earn Rewards: Share in $30,000 USDT + 1,000,000 Super Stakes. 🔹 Lead the Change: Verifiable input → Trusted AI. How to Participate: 1️⃣ Connect your wallet and register. 2️⃣ Claim your 300-point welcome bonus. 3️⃣ Submit links and climb the leaderboard. ✔️ Refer Friends: Get a 35% bonus for every valid link they submit! 👉 Watch the video guide below. 🔗 Start now: Let’s build the next generation of verifiable AI together

Super Protocol

35,784 views • 1 year ago

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this
0:21

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this

Yarchi

32,594 views • 2 months ago

Big update: Super Carl now works in one click, free. But first, the backstory. Claude can’t search LinkedIn. So people started connecting Super Carl to Claude through MCP—giving it access to a LinkedIn-sized dataset covering more than 1 billion people. To be clear: this is not data scraped from LinkedIn. Carl combines licensed partner data, public sources and proprietary data into a continuously updated dataset of people and companies. People started asking Carl to: • Find the perfect hire • Find customers showing buying signals • Run reference checks • Find fresh founders • Find seed investors • Find their next role Then they saw the magic. That’s the Super Carl aha moment. The problem was that too many people never reached it. Some had to wait for their IT team to approve the MCP. Others found the setup too technical. So we removed the setup entirely. As you’ll see in the video, you can now visit on desktop or mobile and choose a ready-made prompt. Make a few quick edits, enter your email and hit Start project. That’s it. Carl runs the entire search directly inside our website, and you’ll see the magic in about 30 seconds. No MCP. No IT approval. No prompt engineering. You can connect Carl to Claude or ChatGPT later—or keep using it directly on our site. Go try it:
0:33

Big update: Super Carl now works in one click, free. But first, the backstory. Claude can’t search LinkedIn. So people started connecting Super Carl to Claude through MCP—giving it access to a LinkedIn-sized dataset covering more than 1 billion people. To be clear: this is not data scraped from LinkedIn. Carl combines licensed partner data, public sources and proprietary data into a continuously updated dataset of people and companies. People started asking Carl to: • Find the perfect hire • Find customers showing buying signals • Run reference checks • Find fresh founders • Find seed investors • Find their next role Then they saw the magic. That’s the Super Carl aha moment. The problem was that too many people never reached it. Some had to wait for their IT team to approve the MCP. Others found the setup too technical. So we removed the setup entirely. As you’ll see in the video, you can now visit on desktop or mobile and choose a ready-made prompt. Make a few quick edits, enter your email and hit Start project. That’s it. Carl runs the entire search directly inside our website, and you’ll see the magic in about 30 seconds. No MCP. No IT approval. No prompt engineering. You can connect Carl to Claude or ChatGPT later—or keep using it directly on our site. Go try it:

Ben Keighran

190,836 views • 1 month ago

We have released the Gaza Node Map: every event, location, person, video, soldier, strike, victim, journalist, etc - are mapped out as a nodes, and each node linked with it's related nodes for researchers. It includes: 92,588 events 159,520 links 3,440 fascilities 715 Actors/IDF units 21,427 strikes Fully searchable index Downloadable database Dossier per node with related events & source links Generate report button per node & node groups It can be accessed here: Please re-share & quote tweet to help it break out of the algorithm. This is a slice of the data, we are uploading the rest of it as fast as possible. If you want to submit footage or give feedback / report a bug, join our telegram (linked in bio). Thanks to everyone invovled in this project. This is a beta so expect bugs & errors, especially on mobile devices - we suggest you use a PC. Follow our backups Zionism Exposed & Israel Exposed عربي God bless.
2:04

We have released the Gaza Node Map: every event, location, person, video, soldier, strike, victim, journalist, etc - are mapped out as a nodes, and each node linked with it's related nodes for researchers. It includes: 92,588 events 159,520 links 3,440 fascilities 715 Actors/IDF units 21,427 strikes Fully searchable index Downloadable database Dossier per node with related events & source links Generate report button per node & node groups It can be accessed here: Please re-share & quote tweet to help it break out of the algorithm. This is a slice of the data, we are uploading the rest of it as fast as possible. If you want to submit footage or give feedback / report a bug, join our telegram (linked in bio). Thanks to everyone invovled in this project. This is a beta so expect bugs & errors, especially on mobile devices - we suggest you use a PC. Follow our backups Zionism Exposed & Israel Exposed عربي God bless.

Israel Exposed

713,355 views • 4 days ago

How should you search, filter, and paginate data with Next.js? This demo has 50,000 books in a Postgres database. • Page Load: When the page loads, we see the React Suspense fallback. This loading skeleton is displayed until the first page of books is retrieved from the database. • Searching: The search input has a 200ms debounce. After 200ms of inactivity, the form submits, updating the URL state with `?q={search}`. The Server Component reads `searchParams` and queries the database. On form submission, a React transition starts, allowing us to read the pending status with `useFormStatus` to display an inline loading state. • State Preservation: Navigating to an individual book page retains the search input state. Reloading the page or sharing the link preserves the search results. • Client-side Filtering: Filtering authors in the left sidebar is done client-side. Authors are fetched by a Server Component and passed as props to the sidebar. Changing the input value updates React state and re-renders the sidebar. • Optimistic Updates: The sidebar’s selected authors are optimistically updated with `useOptimistic`. Checkbox selections update instantly without waiting for the URL to change. • State Preservation: Navigating to an individual book page retains the sidebar filter input and selected author state across navigations, giving it an app-like feel. • Pagination: Navigating between pages updates the URL state, triggering the Server Component to query the database for the specific page of books. We also fetch the total book count to show the total number of pages. This demo isn't perfect yet (still working on it) but it's been a fun playground for some of these patterns. You can imagine a similar experience for thousands of movies, cars, products, or any other very large dataset. Demo → Code →
0:22

How should you search, filter, and paginate data with Next.js? This demo has 50,000 books in a Postgres database. • Page Load: When the page loads, we see the React Suspense fallback. This loading skeleton is displayed until the first page of books is retrieved from the database. • Searching: The search input has a 200ms debounce. After 200ms of inactivity, the form submits, updating the URL state with `?q={search}`. The Server Component reads `searchParams` and queries the database. On form submission, a React transition starts, allowing us to read the pending status with `useFormStatus` to display an inline loading state. • State Preservation: Navigating to an individual book page retains the search input state. Reloading the page or sharing the link preserves the search results. • Client-side Filtering: Filtering authors in the left sidebar is done client-side. Authors are fetched by a Server Component and passed as props to the sidebar. Changing the input value updates React state and re-renders the sidebar. • Optimistic Updates: The sidebar’s selected authors are optimistically updated with `useOptimistic`. Checkbox selections update instantly without waiting for the URL to change. • State Preservation: Navigating to an individual book page retains the sidebar filter input and selected author state across navigations, giving it an app-like feel. • Pagination: Navigating between pages updates the URL state, triggering the Server Component to query the database for the specific page of books. We also fetch the total book count to show the total number of pages. This demo isn't perfect yet (still working on it) but it's been a fun playground for some of these patterns. You can imagine a similar experience for thousands of movies, cars, products, or any other very large dataset. Demo → Code →

Lee Robinson

236,915 views • 2 years ago

The job of a marketing engineer is to pull signals into one system and turn them into pipeline. Here is an example of an SEO/AEO workflow: 1) Read Google Search Console 2) Pull the keyword data from Ahrefs or SEMrush 3) Look in the CMS to find out if the post is already there 4) Put the keywords in order by search volume and buyer intent 5) Read the pages that are at the top of the results now 6) Add the founder's point of view 7) Write the post, the meta title and the internal links Then the agent sends all of it to a person for approval. The agent can only do this if you connect it to your live business data and your tools. "The tools are going to keep changing, but the workflow is the thing to actually learn." Learn the workflow first.
1:08

The job of a marketing engineer is to pull signals into one system and turn them into pipeline. Here is an example of an SEO/AEO workflow: 1) Read Google Search Console 2) Pull the keyword data from Ahrefs or SEMrush 3) Look in the CMS to find out if the post is already there 4) Put the keywords in order by search volume and buyer intent 5) Read the pages that are at the top of the results now 6) Add the founder's point of view 7) Write the post, the meta title and the internal links Then the agent sends all of it to a person for approval. The agent can only do this if you connect it to your live business data and your tools. "The tools are going to keep changing, but the workflow is the thing to actually learn." Learn the workflow first.

The Startup Ideas Podcast (SIP) 🧃

23,448 views • 9 days ago

66,000. That’s the amount of people Ben Schwartz & Friends has played to since we started touring last year. 66,000! I am blown away by the support and love from each and every city we brought long form improv to. Thank you. I have also heard time and time again from staff or merch vendors how kind the audiences have been to everyone. Makes me so happy. ❤️ And thank you to the incredible improvisers who joined me on stage throughout America, Canada and England. You made every city so special, unique and hilarious. You are some of the funniest people on the planet. If you came to a watch a show in the past year and a half, put a favorite moment or inside joke from the show in the comments below. Can’t wait to be reminded of all the goofs. Keep an eye on for 2024 tour dates. Some cities already announced, a whole bunch more coming soon! See ya next year.
1:28

66,000. That’s the amount of people Ben Schwartz & Friends has played to since we started touring last year. 66,000! I am blown away by the support and love from each and every city we brought long form improv to. Thank you. I have also heard time and time again from staff or merch vendors how kind the audiences have been to everyone. Makes me so happy. ❤️ And thank you to the incredible improvisers who joined me on stage throughout America, Canada and England. You made every city so special, unique and hilarious. You are some of the funniest people on the planet. If you came to a watch a show in the past year and a half, put a favorite moment or inside joke from the show in the comments below. Can’t wait to be reminded of all the goofs. Keep an eye on for 2024 tour dates. Some cities already announced, a whole bunch more coming soon! See ya next year.

Ben Schwartz

91,393 views • 2 years ago

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!
19:19

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

Santiago

110,133 views • 1 year ago

Shortly before midnight, we had multiple reports sent in of an extremely bright green flash in the sky to the north. We went back in our database of Aurora cameras to find the culprit… and here it is!! The Manistee camera had the best angle as the object streaked across the northern sky. You can even pick up on a faint auroral glow at the same time! Not only that, but you can see the streak left behind from the flash after it occurred. Time was 11:13 PM EDT and approximately 35 seconds, October 29th, 2025, for those who’d also like to check any home security cameras.
0:21

Shortly before midnight, we had multiple reports sent in of an extremely bright green flash in the sky to the north. We went back in our database of Aurora cameras to find the culprit… and here it is!! The Manistee camera had the best angle as the object streaked across the northern sky. You can even pick up on a faint auroral glow at the same time! Not only that, but you can see the streak left behind from the flash after it occurred. Time was 11:13 PM EDT and approximately 35 seconds, October 29th, 2025, for those who’d also like to check any home security cameras.

Michigan Storm Chasers

19,432 views • 10 months ago

PhD Students – How to identify top researchers in your research area? First, why it is important to know top researchers in your research area. 1️⃣ Help you identify top papers 2️⃣ Help you to collaborate with top researchers 3️⃣ Help you to learn from their work 4️⃣ Help you find your research ideals 🎯 Use Bohrium to identify the top researchers. 👉 Here is how it works? 1. Go to and log in. 2. From the left side menu, click Scholars. 3. In the search box, enter your research area. 4. For example, I entered cloud computing. 5. Bohrium will display the ranked list of top researchers. 6. This list is based on the number of citations for the researcher. 7. Then, click on the researcher’s name. 8. It will display the entire profile of the researcher. 9. This profile contains the work history of the researcher. 10. It contains the research areas of the researcher. 11. You will see the number of papers and citations. 12. You can sort the papers based on the latest/most cited. 13. You will also see the co-authors of the researcher. Once explored, you can go back and explore another researcher. This way you will know the top researchers in your research area. Bohrium has a large database of 20 million active scholars 🎗️Try Bohrium to find top researchers Bohrium Link: ❄️ Anything you'd like to add?
0:29

PhD Students – How to identify top researchers in your research area? First, why it is important to know top researchers in your research area. 1️⃣ Help you identify top papers 2️⃣ Help you to collaborate with top researchers 3️⃣ Help you to learn from their work 4️⃣ Help you find your research ideals 🎯 Use Bohrium to identify the top researchers. 👉 Here is how it works? 1. Go to and log in. 2. From the left side menu, click Scholars. 3. In the search box, enter your research area. 4. For example, I entered cloud computing. 5. Bohrium will display the ranked list of top researchers. 6. This list is based on the number of citations for the researcher. 7. Then, click on the researcher’s name. 8. It will display the entire profile of the researcher. 9. This profile contains the work history of the researcher. 10. It contains the research areas of the researcher. 11. You will see the number of papers and citations. 12. You can sort the papers based on the latest/most cited. 13. You will also see the co-authors of the researcher. Once explored, you can go back and explore another researcher. This way you will know the top researchers in your research area. Bohrium has a large database of 20 million active scholars 🎗️Try Bohrium to find top researchers Bohrium Link: ❄️ Anything you'd like to add?

Faheem Ullah

91,106 views • 8 months ago

DISCLAIMER: FRAUD ALERT It has come to the attention of Channel One TV that a fraudulent AI-generated video is being circulated bearing the Channel One TV set and the image of one of our journalists, in an attempt to scam unsuspecting members of the public. We wish to state categorically that: •⁠ ⁠This video is NOT from Channel One TV. •⁠ ⁠It has NOT been produced, endorsed, or authorized by Channel One TV or any of our journalists. •⁠ ⁠The content is false, deceptive, and malicious. We urge everyone to immediately ignore the video and to report it on the platform where you see it. Do NOT engage with or respond to any requests or links associated with it. Channel One TV remains committed to professional journalism and the highest ethical standards. We are working with the appropriate authorities to investigate this matter and bring the perpetrators to justice. Stay vigilant. Protect yourself. — Channel One TV Management
1:26

DISCLAIMER: FRAUD ALERT It has come to the attention of Channel One TV that a fraudulent AI-generated video is being circulated bearing the Channel One TV set and the image of one of our journalists, in an attempt to scam unsuspecting members of the public. We wish to state categorically that: •⁠ ⁠This video is NOT from Channel One TV. •⁠ ⁠It has NOT been produced, endorsed, or authorized by Channel One TV or any of our journalists. •⁠ ⁠The content is false, deceptive, and malicious. We urge everyone to immediately ignore the video and to report it on the platform where you see it. Do NOT engage with or respond to any requests or links associated with it. Channel One TV remains committed to professional journalism and the highest ethical standards. We are working with the appropriate authorities to investigate this matter and bring the perpetrators to justice. Stay vigilant. Protect yourself. — Channel One TV Management

ChannelOne TV

111,688 views • 1 year ago

Robert Kennedy Jr. wants to do the most basic thing science can do - compare the health outcomes of vaccinated children to unvaccinated children using the largest medical database in America. That's it. That's the study. That's the scientific method. And the American Academy of Pediatrics is suing him to stop it. Think about what that means. Not content with blocking changes to the vaccine schedule, they are now going to court to prevent an investigation into whether the schedule is actually producing healthy children. The one question the entire program should have been answering for fifty years, and the people who run that program are fighting in federal court to make sure it never gets asked. This is an industry protecting itself from its own data. I am not accusing anyone in medicine of malice. I am saying that the long-term health investigation has never been done with the seriousness it deserves, and now that someone is finally trying to do it, there is a worldwide effort to shut it down before it starts. We have to do this study. We have databases right now, like the Henry Ford Health database, that could give us real answers. Every database in this country should be opened to this investigation. The scientific method demands it. The health of our children demands it. The only people who have something to fear from the truth are the ones fighting this hard to hide from it.
0:53

Robert Kennedy Jr. wants to do the most basic thing science can do - compare the health outcomes of vaccinated children to unvaccinated children using the largest medical database in America. That's it. That's the study. That's the scientific method. And the American Academy of Pediatrics is suing him to stop it. Think about what that means. Not content with blocking changes to the vaccine schedule, they are now going to court to prevent an investigation into whether the schedule is actually producing healthy children. The one question the entire program should have been answering for fifty years, and the people who run that program are fighting in federal court to make sure it never gets asked. This is an industry protecting itself from its own data. I am not accusing anyone in medicine of malice. I am saying that the long-term health investigation has never been done with the seriousness it deserves, and now that someone is finally trying to do it, there is a worldwide effort to shut it down before it starts. We have to do this study. We have databases right now, like the Henry Ford Health database, that could give us real answers. Every database in this country should be opened to this investigation. The scientific method demands it. The health of our children demands it. The only people who have something to fear from the truth are the ones fighting this hard to hide from it.

Del Bigtree

434,332 views • 4 months ago

REAL ESTATE PEOPLE WILL HATE HIM FOR THIS. HE BUILT A CLAUDE AGENT THAT TURNS ANY LISTING INTO A SELLABLE VIDEO ON ITS OWN Playbook: connect Claude to a video generator, paste a listing, get a cinematic tour of every room, sell it to the agent But typing the prompt for every listing doesn't scale. He turned it into a skill his Claude runs on its own Here's how to build the automated version: 1. Connect the video engine once. In Claude, go to Customize, Connectors, Add Custom Connector, name it Higgsfield, and paste the server URL from higgsfield. ai/mcp. Authenticate through your account. No API keys. Now Claude can generate video straight from chat 2. Turn the workflow into a skill. Instead of pasting the same prompt every time, have Claude build a skill. Tell it: "Create a skill called listing-to-video. When I give it a listing URL, scrape the room photos, generate a cinematic clip of each room with Higgsfield, and save them to a folder." Now the whole process is one command, not a wall of text 3. Let the agent run the listing. Hand it a URL and say "run listing-to-video on this." It pulls the photos, fires each room through the video model, and brings the clips back. You wrote the prompt once, inside the skill. You never write it again 4. Stitch and deliver. Drop the clips together into one tour. Send a free sample to the listing's agent, then charge per video or a monthly rate for ongoing listings 5. Scale it with your team. Add a skill that drafts the outreach email and one that builds a simple landing page for the agent. Now one operator runs sourcing, production, and pitching from a single Claude session The edge isn't generating one video. It's building the skill once so every future listing runs itself Bookmark this
0:42

REAL ESTATE PEOPLE WILL HATE HIM FOR THIS. HE BUILT A CLAUDE AGENT THAT TURNS ANY LISTING INTO A SELLABLE VIDEO ON ITS OWN Playbook: connect Claude to a video generator, paste a listing, get a cinematic tour of every room, sell it to the agent But typing the prompt for every listing doesn't scale. He turned it into a skill his Claude runs on its own Here's how to build the automated version: 1. Connect the video engine once. In Claude, go to Customize, Connectors, Add Custom Connector, name it Higgsfield, and paste the server URL from higgsfield. ai/mcp. Authenticate through your account. No API keys. Now Claude can generate video straight from chat 2. Turn the workflow into a skill. Instead of pasting the same prompt every time, have Claude build a skill. Tell it: "Create a skill called listing-to-video. When I give it a listing URL, scrape the room photos, generate a cinematic clip of each room with Higgsfield, and save them to a folder." Now the whole process is one command, not a wall of text 3. Let the agent run the listing. Hand it a URL and say "run listing-to-video on this." It pulls the photos, fires each room through the video model, and brings the clips back. You wrote the prompt once, inside the skill. You never write it again 4. Stitch and deliver. Drop the clips together into one tour. Send a free sample to the listing's agent, then charge per video or a monthly rate for ongoing listings 5. Scale it with your team. Add a skill that drafts the outreach email and one that builds a simple landing page for the agent. Now one operator runs sourcing, production, and pitching from a single Claude session The edge isn't generating one video. It's building the skill once so every future listing runs itself Bookmark this

Yarchi

54,840 views • 3 months ago

The infrastructure for working with video data at scale barely exists. Grass Video Search is our first step in changing that. You can now find anything in a video based on the contents of its frames, not just transcripts or tags. Over the last several months, the Grass Foundation has quietly assembled one of the largest video datasets in history: over a billion videos from across the public web, and is segmenting them by scene with VLM annotations of keyframes. This dataset is now searchable, so you can find the exact moment a visual, pattern, or concept appears. Curation has always been the bottleneck in video analysis. We built a system that automates it. This is just the beginning. Over 4 billion additional videos are queued for processing, and the index is growing daily. We’re opening access to a limited set of collaborators. If you’re a researcher, journalist, or nonprofit working with video, archives, or large-scale analysis, we’d love to hear from you.
0:45

The infrastructure for working with video data at scale barely exists. Grass Video Search is our first step in changing that. You can now find anything in a video based on the contents of its frames, not just transcripts or tags. Over the last several months, the Grass Foundation has quietly assembled one of the largest video datasets in history: over a billion videos from across the public web, and is segmenting them by scene with VLM annotations of keyframes. This dataset is now searchable, so you can find the exact moment a visual, pattern, or concept appears. Curation has always been the bottleneck in video analysis. We built a system that automates it. This is just the beginning. Over 4 billion additional videos are queued for processing, and the index is growing daily. We’re opening access to a limited set of collaborators. If you’re a researcher, journalist, or nonprofit working with video, archives, or large-scale analysis, we’d love to hear from you.

Grass

471,705 views • 1 year ago

We are releasing Genamon, an open source project that shows how to make a Generative AI driven game in Unity with these features: * ChatGPT makes the creature description * Scenario generates the art from the description * mints the new creature out the @0xPolygonLabs blockchain—so now you could trade it on open exchanges * all the cloud-based services use Beamable to define content, store inventory, and run microservices to operative generative and blockchain links from the cloud Source code showing how to do all of the above is right here: #generativeai #ai #artificialintelligence #blockchain #unity #gpt
1:01

We are releasing Genamon, an open source project that shows how to make a Generative AI driven game in Unity with these features: * ChatGPT makes the creature description * Scenario generates the art from the description * mints the new creature out the @0xPolygonLabs blockchain—so now you could trade it on open exchanges * all the cloud-based services use Beamable to define content, store inventory, and run microservices to operative generative and blockchain links from the cloud Source code showing how to do all of the above is right here: #generativeai #ai #artificialintelligence #blockchain #unity #gpt

Jon Radoff 👾/acc 🎮 Metavert

97,036 views • 3 years ago