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.

this is probably the best AI web scraping tool i have found so far: - easy to use - completely free - super clean response in markdown format this means i can feed my LLM better and cleaner data + consume less tokens!

Fekri

12,065 subscribers

265,084 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This AI Motion Brush tool is insane! It lets you control the movement and actions of 5 different objects simultaneously. It's the only AI tool can do blocking for AI filmmaking so far. You have free credits to try on Kling AI, link in comments! Here’s how to get started:

This AI Motion Brush tool is insane! It lets you control the movement and actions of 5 different objects simultaneously. It's the only AI tool can do blocking for AI filmmaking so far. You have free credits to try on Kling AI, link in comments! Here’s how to get started:

el.cine

159,502 views • 1 year ago

I have found a quicker way to grind than using paletools Best thing is it’s free and you can have paletools and this active at the same time This is how quick you can turn your dupes into pps. Any questions comment and i’ll try help best i can

I have found a quicker way to grind than using paletools Best thing is it’s free and you can have paletools and this active at the same time This is how quick you can turn your dupes into pps. Any questions comment and i’ll try help best i can

Yapper

257,700 views • 1 year ago

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

Dan McAteer

17,164 views • 1 month ago

i added this for discord /export defaults to markdown, also supports json reads directly from discord, no data is saved so you can use it on channels with indexing disabled as well

i added this for discord /export defaults to markdown, also supports json reads directly from discord, no data is saved so you can use it on channels with indexing disabled as well

Rhys

31,729 views • 6 months ago

🤯 Found another great use case for Depth today! I tried recreating this fashion transformation video with my own character, but the original character kept showing up. 🌟 So I switched the reference video to Depth, and it worked way better! Same motion and timing, but now I can use my own character and completely new outfits! Quick workflow in the comments Full Depth workflow in the quoted post 👇

🤯 Found another great use case for Depth today! I tried recreating this fashion transformation video with my own character, but the original character kept showing up. 🌟 So I switched the reference video to Depth, and it worked way better! Same motion and timing, but now I can use my own character and completely new outfits! Quick workflow in the comments Full Depth workflow in the quoted post 👇

Larus Canus

108,705 views • 15 days ago

Just found out THIS meme is AI. Remade it in blender so i can use it ethically lol do yall like it?

Just found out THIS meme is AI. Remade it in blender so i can use it ethically lol do yall like it?

JoJoJosiah

83,986 views • 1 month ago

wow, this new AI is incredible Promptly can generate prompts for specific AI models like ChatGPT, Midjourney, many video generators and.. guide you how to make it better, this is super useful free to use now 7 examples:

wow, this new AI is incredible Promptly can generate prompts for specific AI models like ChatGPT, Midjourney, many video generators and.. guide you how to make it better, this is super useful free to use now 7 examples:

el.cine

130,220 views • 1 year ago

Stop using Blender. Stop using Element 3D. I found the best website where you can create device animations for free.. It’s super easy to use, feels premium and save hours of time. Want to see what it is? Follow and comment “C” and I’ll send it over!

Stop using Blender. Stop using Element 3D. I found the best website where you can create device animations for free.. It’s super easy to use, feels premium and save hours of time. Want to see what it is? Follow and comment “C” and I’ll send it over!

Rowaifa

56,295 views • 1 year ago

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.

elvis

31,242 views • 3 months ago

Turn complex docs into clean, LLM-ready data! Every AI company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!

Turn complex docs into clean, LLM-ready data! Every AI company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!

Akshay 🚀

58,172 views • 8 months ago

I can't say enough great things about our new Matic Robots. Here is what I love about it so far: - The unboxing experience is super thoughtful - The mobile app is apple-like - The AI in this little guy is shockingly good, from mapping the house to never sucking up a sock or power cord again! - It is quiet. Really quiet! I can actually let it run while I'm on a Zoom call. This is a first. - Perhaps the craziest thing of all is how your floors feel after mopping. My wife and I both thought the same thing, our floors have never felt so clean. It reminds me of the first time I used a Soniccare tooth brush. I couldn't believe how clean my teeth felt. I don't know what magic they have in this thing but it is awesome. If you end up buying one, use this link and you will get some nice freebies -

I can't say enough great things about our new Matic Robots. Here is what I love about it so far: - The unboxing experience is super thoughtful - The mobile app is apple-like - The AI in this little guy is shockingly good, from mapping the house to never sucking up a sock or power cord again! - It is quiet. Really quiet! I can actually let it run while I'm on a Zoom call. This is a first. - Perhaps the craziest thing of all is how your floors feel after mopping. My wife and I both thought the same thing, our floors have never felt so clean. It reminds me of the first time I used a Soniccare tooth brush. I couldn't believe how clean my teeth felt. I don't know what magic they have in this thing but it is awesome. If you end up buying one, use this link and you will get some nice freebies -

Chad Bockius

14,264 views • 11 months ago

this is the wildest website I’ve found so far.. it can: – rename 100s of files with AI – auto-organize into folders – work locally.. and it’s 100% FREE link to access below:

this is the wildest website I’ve found so far.. it can: – rename 100s of files with AI – auto-organize into folders – work locally.. and it’s 100% FREE link to access below:

Nelly;

188,609 views • 1 year ago

Today, we're launching the ultimate guide for founders on how to start a lean, AI-native startup in 2025. This covers every single tool founders should use when building their startup from the ground up, from legal, finance, payroll, sales, tech and more. My coauthor Deedy and I have both built Glean and Super[.]com into both $100M+ ARR businesses and we've invested in 100+ startups between us in the last few years, and this is a constant question we get. And it's completely free👇

Today, we're launching the ultimate guide for founders on how to start a lean, AI-native startup in 2025. This covers every single tool founders should use when building their startup from the ground up, from legal, finance, payroll, sales, tech and more. My coauthor Deedy and I have both built Glean and Super[.]com into both $100M+ ARR businesses and we've invested in 100+ startups between us in the last few years, and this is a constant question we get. And it's completely free👇

Henry Shi

10,228 views • 11 months ago

Hey everyone! I know I don’t have to explain myself but just doing so for the people who are new to my feed or just found me. I have a full-time day job so I can’t really respond to messages during weekdays. I am only free during weekends. 😊 My day job is very stressful so I reserve all content related stuff for weekends. This may change soon though 😉 You can subscribe to my site to help me. 🤣 I’ll post when I am free to accept customs/Skype. 💋

Hey everyone! I know I don’t have to explain myself but just doing so for the people who are new to my feed or just found me. I have a full-time day job so I can’t really respond to messages during weekdays. I am only free during weekends. 😊 My day job is very stressful so I reserve all content related stuff for weekends. This may change soon though 😉 You can subscribe to my site to help me. 🤣 I’ll post when I am free to accept customs/Skype. 💋

pilifeetnas

18,737 views • 2 years ago

Gillian Keegan's bonkers response to losing, "Volatility in politics is the story.. What it means and what it means for the future, I don't know" Can anyone translate this for me?

Gillian Keegan's bonkers response to losing, "Volatility in politics is the story.. What it means and what it means for the future, I don't know" Can anyone translate this for me?

Farrukh

90,965 views • 2 years ago

In response to the people posting idiotic replies, I just found this. If you don't have a better answer, consider not posting anything at all.

In response to the people posting idiotic replies, I just found this. If you don't have a better answer, consider not posting anything at all.

Crowdsource The Truth

48,102 views • 10 months ago

This is how I like to imagine the call and response in So What.

This is how I like to imagine the call and response in So What.

Lonious Thee Monk

568,287 views • 2 years ago

Ok guys, time to come clean: my diabolical plan was to use shaders to merge the GPU particles and create some sort of fluid simulations inside Godot. This is proving difficult, also the particles interact with the collider but not with each other, so this is probably impossible. I don't know if this can spark some idea in the brain of someone more technical than me.

Ok guys, time to come clean: my diabolical plan was to use shaders to merge the GPU particles and create some sort of fluid simulations inside Godot. This is proving difficult, also the particles interact with the collider but not with each other, so this is probably impossible. I don't know if this can spark some idea in the brain of someone more technical than me.

FR3NKD

13,363 views • 2 years ago