Loading video...

Video Failed to Load

Go Home

I'm very impressed with Venice's YouTube summarization tool. I fed it a 55 minute Dutch podcast, and in just 115 seconds, it had already downloaded the audio, transcribed it, and produced a summary. I then had to translate it from English to Dutch, which took a few more seconds....

WellerOlaf's profile picture

Olaf Weller

1,094 subscribers

24,402 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

@ollybromham For the time, I just had a hunch how it should move and feel. I pulled some of the variables into sliders and built a little 'design tool' which allowed me to fidget around with the values and feel it out (this makes SwiftUI such a neat prototyping tool!) :-)
0:22

@ollybromham For the time, I just had a hunch how it should move and feel. I pulled some of the variables into sliders and built a little 'design tool' which allowed me to fidget around with the values and feel it out (this makes SwiftUI such a neat prototyping tool!) :-)

Alex Widua

11,071 views • 2 years ago

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities
7:50

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

Yohei

211,889 views • 1 year ago

Erik Voorhees explains how Venice's dual token model actually works "You can stake 100 VVV to get pro access to Venice. We take a bunch of our revenue, buy the token, and burn it" "We want to take that to its extreme and try to buy every last token we can and burn it all" "You lock up VVV to mint DIEM. Each DIEM you hold gives you $1/day to use on any AI model you want" "We built it so AI agents could hold an asset and get marginally free inference" "It changes the economic calculation. We thought that'd be an interesting design space to explore"
2:23

Erik Voorhees explains how Venice's dual token model actually works "You can stake 100 VVV to get pro access to Venice. We take a bunch of our revenue, buy the token, and burn it" "We want to take that to its extreme and try to buy every last token we can and burn it all" "You lock up VVV to mint DIEM. Each DIEM you hold gives you $1/day to use on any AI model you want" "We built it so AI agents could hold an asset and get marginally free inference" "It changes the economic calculation. We thought that'd be an interesting design space to explore"

Market Bubble

136,094 views • 2 months ago

OK. You wanna see something amazing? Google AI has put together an extraordinary tool where you can put AI and learning to use. I'm a HUGE audio learner so I wanted to give it a test. I gave Google Notebook LLM the Federal Register (from today) and then produced a podcast based on the content. It's pretty cool how it comes out. I uploaded the FedReg and told it what to do and it composed a 9-minute podcast with two hosts about the crazy stuff our govt does every day.
9:27

OK. You wanna see something amazing? Google AI has put together an extraordinary tool where you can put AI and learning to use. I'm a HUGE audio learner so I wanted to give it a test. I gave Google Notebook LLM the Federal Register (from today) and then produced a podcast based on the content. It's pretty cool how it comes out. I uploaded the FedReg and told it what to do and it composed a 9-minute podcast with two hosts about the crazy stuff our govt does every day.

Justin Hart

32,106 views • 1 year ago

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)
1:18

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 views • 1 year ago

Here’s my POSITIVE ad for the FINAL week. This one’s a minute long because I had too much to say to fit into thirty seconds! Let me know what you think. If you like it and want to help me broadcast it, please chip in here:
0:59

Here’s my POSITIVE ad for the FINAL week. This one’s a minute long because I had too much to say to fit into thirty seconds! Let me know what you think. If you like it and want to help me broadcast it, please chip in here:

Thomas Massie for Congress

1,621,917 views • 2 months ago

Q: You've won with three different teams, but still I can say because I'm older than you, you're much older now. Is this like being reborn? "Yes, for sure. That's what I said to the guys, I said, not bad for a 41-year-old, eh?" 😭 "No. I've trained very, very, very, very hard this year. I mean last year was just, it was difficult from the beginning because I got injured here actually. Big crash that I had here last year and I was carrying that injury through the whole year which was really, really difficult. And then just, God, just the whole year, I just never want to think about it. But I never gave up, refocused, recentred, had a great winter, came back in pushing with these guys and rejigged my team." "Wow. This has come sooner than I had expected, but yeah, I take it. I'm so, so happy and so happy for the team as well." F1 2026 || Barcelona
1:01

Q: You've won with three different teams, but still I can say because I'm older than you, you're much older now. Is this like being reborn? "Yes, for sure. That's what I said to the guys, I said, not bad for a 41-year-old, eh?" 😭 "No. I've trained very, very, very, very hard this year. I mean last year was just, it was difficult from the beginning because I got injured here actually. Big crash that I had here last year and I was carrying that injury through the whole year which was really, really difficult. And then just, God, just the whole year, I just never want to think about it. But I never gave up, refocused, recentred, had a great winter, came back in pushing with these guys and rejigged my team." "Wow. This has come sooner than I had expected, but yeah, I take it. I'm so, so happy and so happy for the team as well." F1 2026 || Barcelona

sim 🇧🇷🇲🇽🇸🇳🇫🇷🇭🇹

128,391 views • 1 month ago

My work for #HelluvaBoss Season 02 Episode 11! I'm in love with this whole musical number 🌟 and I'm very happy I got to be in it! (I'm also very happy I got to do a few secs of Andrealphus❄️)
0:29

My work for #HelluvaBoss Season 02 Episode 11! I'm in love with this whole musical number 🌟 and I'm very happy I got to be in it! (I'm also very happy I got to do a few secs of Andrealphus❄️)

Julia Calle

54,420 views • 1 year ago

Made a tool lets you use noise to paint terrain materials, with a whitelist too. The noise is optional and if you turn it off it just acts as a (in my opinion) better paint tool. Makes large scale terrain painting a lot easier for me. May release it soon:) #Roblox #RobloxDev
1:01

Made a tool lets you use noise to paint terrain materials, with a whitelist too. The noise is optional and if you turn it off it just acts as a (in my opinion) better paint tool. Makes large scale terrain painting a lot easier for me. May release it soon:) #Roblox #RobloxDev

tyridge77

20,801 views • 3 years ago

On a previous #TeawithGaryVee I was asked "I'm 46 years old and have been very successful in the restaurant business, I'm making more money than I could dream of but this is a tough and demanding business, part of me just wants to sell everything and downgrade my life to do what I truly love, what's your advice?" If you have a question for me, drop it here so my team can add it to the next Rapid Fire Q&A and follow me on
4:50

On a previous #TeawithGaryVee I was asked "I'm 46 years old and have been very successful in the restaurant business, I'm making more money than I could dream of but this is a tough and demanding business, part of me just wants to sell everything and downgrade my life to do what I truly love, what's your advice?" If you have a question for me, drop it here so my team can add it to the next Rapid Fire Q&A and follow me on

Gary Vaynerchuk

33,625 views • 10 months ago

I opened with “Mr. President” — Aleksandr Lukashenko laughed it off. First few seconds with the President, and you could already feel it. He’s alive and real — some interviews take time to find a rhythm, but this one had it immediately.
0:25

I opened with “Mr. President” — Aleksandr Lukashenko laughed it off. First few seconds with the President, and you could already feel it. He’s alive and real — some interviews take time to find a rhythm, but this one had it immediately.

Rick Sanchez

38,052 views • 3 months ago

Sean Astin reveals he was paid only $75,000 per movie for Lord of the Rings and was forced to sell his house right after making the trilogy ​"I didn't get paid very well for Lord of the Rings" ​"I had to sell my house afterwards... we bought a house up in the hills with a view, and the business manager said to me, 'You have to make 250 grand a year based on how you spend your money'" ​"Then I got offered Lord of the Rings, and it was an offer for 250,000 for a year and a half" ​"And I was like, 'Wait a minute, my pen signed this contract which obligated me to 250 a year, and I'm gonna sign this contract which will make it so that I cannot satisfy that other thing'" ​"So it was 75 grand a movie... 75 grand a movie was what you got" ​"And how about residuals for that? No residuals"
1:29

Sean Astin reveals he was paid only $75,000 per movie for Lord of the Rings and was forced to sell his house right after making the trilogy ​"I didn't get paid very well for Lord of the Rings" ​"I had to sell my house afterwards... we bought a house up in the hills with a view, and the business manager said to me, 'You have to make 250 grand a year based on how you spend your money'" ​"Then I got offered Lord of the Rings, and it was an offer for 250,000 for a year and a half" ​"And I was like, 'Wait a minute, my pen signed this contract which obligated me to 250 a year, and I'm gonna sign this contract which will make it so that I cannot satisfy that other thing'" ​"So it was 75 grand a movie... 75 grand a movie was what you got" ​"And how about residuals for that? No residuals"

Nichole

479,509 views • 11 days ago

"i'm studying english these days very very very hard" "i've come up with a goal, but i can't tell you what it is" "once i reach my goal, i tell you what it was then, wait for it" like what if the goal was partly related to this!!
1:04

"i'm studying english these days very very very hard" "i've come up with a goal, but i can't tell you what it is" "once i reach my goal, i tell you what it was then, wait for it" like what if the goal was partly related to this!!

roxie‎‎ 🥫🍋

211,144 views • 6 months ago

✨ Also made a new [ ✂️ Crop ] feature in Photo AI because before users would use the embedded Photopea editor for that I thought this would be very hard to do myself And again I asked Claude Code, and it one shotted it, then I tweaked it a bit and asked it to add iOS-style zoom crop, where if you zoom (on laptop just scrolling the mouse or trackpad) it would not scale the crop selection, but zoom the entire pic while the crop selection stayed the same Miraculously it just worked, again I would not be able to make this myself, it'd take me ages, probably a week of suffering, this took me 30 minutes and was a blast So in this case I'm something like 150x more efficient!
0:59

✨ Also made a new [ ✂️ Crop ] feature in Photo AI because before users would use the embedded Photopea editor for that I thought this would be very hard to do myself And again I asked Claude Code, and it one shotted it, then I tweaked it a bit and asked it to add iOS-style zoom crop, where if you zoom (on laptop just scrolling the mouse or trackpad) it would not scale the crop selection, but zoom the entire pic while the crop selection stayed the same Miraculously it just worked, again I would not be able to make this myself, it'd take me ages, probably a week of suffering, this took me 30 minutes and was a blast So in this case I'm something like 150x more efficient!

@levelsio

62,521 views • 1 year ago

I am a live, radio guy. I want to be the guy you turn to for live, breaking news and live radio. But more and more it is obvious I have to grow my podcast and could use your help. If you would subscribe to my podcast in your favorite podcasting app, I would very much appreciate it.
1:10

I am a live, radio guy. I want to be the guy you turn to for live, breaking news and live radio. But more and more it is obvious I have to grow my podcast and could use your help. If you would subscribe to my podcast in your favorite podcasting app, I would very much appreciate it.

Erick Erickson

12,449 views • 2 years ago

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."
4:16

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 views • 5 months ago

The post-match interview with captain Simone Gianelli, his mentality:"I'm very competitive, I don't like losing, and when I lose, I take responsibility." 🔥 Simo: I'm very happy with the match. As I was telling you before this match, we needed to figure out what we could do better. I think we figured it out and did it. So I'm very happy for the team, for all the players, because they deserved to be in the top four in the world, and we did it with a convincing performance, I'd say. So I'm very, very happy. My teammates were really good, they played an extraordinary match. - You just mentioned it, we talked about it a few days ago in an interview. You said, 'I rewatched the match against Belgium, I know exactly what we have to do now.' Where does all this calmness come from? Because Fefe also said it: 'We analyze it, Simone looks at his game, I look at mine, we don't always agree, but here it ends well.' Simo: "Yes, yes, I don't want to leave anything to chance. I'm very competitive, I don't like losing, and when I lose, I take responsibility. I know what I can do better, and in the first match against Belgium, I didn't play at my best, and I was disappointed about that, not so much for myself personally, but for not having contributed to my team, although fortunately Ricky took care of it and brought the match to a tie-break. So I analyzed it, I watched it again in my room, I analyzed it, and I knew, I was pretty sure, what I could have done better and differently about that part. We're not superheroes, so today it went well and everything else, but basically, I wanted to enter the match more prepared than I had come into the game. - How much did that lob in the first set excite us, Simone, but how much did you look for it, want it, think about it? Simo: You know, I'm not very good at that lob. I usually do it differently. I was talking to the My teammates, that long lob usually comes out a little crooked, a little wrong, but the situation arose, so I said, why not, let's try it, I saw them skip past me, so it went well. -Captain, hats off for today, really, thank you.
1:11

The post-match interview with captain Simone Gianelli, his mentality:"I'm very competitive, I don't like losing, and when I lose, I take responsibility." 🔥 Simo: I'm very happy with the match. As I was telling you before this match, we needed to figure out what we could do better. I think we figured it out and did it. So I'm very happy for the team, for all the players, because they deserved to be in the top four in the world, and we did it with a convincing performance, I'd say. So I'm very, very happy. My teammates were really good, they played an extraordinary match. - You just mentioned it, we talked about it a few days ago in an interview. You said, 'I rewatched the match against Belgium, I know exactly what we have to do now.' Where does all this calmness come from? Because Fefe also said it: 'We analyze it, Simone looks at his game, I look at mine, we don't always agree, but here it ends well.' Simo: "Yes, yes, I don't want to leave anything to chance. I'm very competitive, I don't like losing, and when I lose, I take responsibility. I know what I can do better, and in the first match against Belgium, I didn't play at my best, and I was disappointed about that, not so much for myself personally, but for not having contributed to my team, although fortunately Ricky took care of it and brought the match to a tie-break. So I analyzed it, I watched it again in my room, I analyzed it, and I knew, I was pretty sure, what I could have done better and differently about that part. We're not superheroes, so today it went well and everything else, but basically, I wanted to enter the match more prepared than I had come into the game. - How much did that lob in the first set excite us, Simone, but how much did you look for it, want it, think about it? Simo: You know, I'm not very good at that lob. I usually do it differently. I was talking to the My teammates, that long lob usually comes out a little crooked, a little wrong, but the situation arose, so I said, why not, let's try it, I saw them skip past me, so it went well. -Captain, hats off for today, really, thank you.

joey, and flower 🌼

24,119 views • 10 months ago

We have now fully commissioned the machine after a few hiccups related to an old dying hard drive in the machine PC (it had a 1 gb hard drive!!) could save the machine in the nick of time with the help of a fellow machining junkie who knew how to do it! But the real reason i am writing is that we successfully ran our first 3D program on it and that the program was written entirely using Claude !! I did it myself and it took me a few hours to get it going. The best part of using Claude was that I could ask it to use macros to write the program which meant i could control *all* variables in the program. And it ran like a charm! Rendered on the part a fine finish and a brilliant high to see the part come out better than expected! I set the job myself because I wanted to get a feel for the machine, its ways and how to work with it. It had been nearly 15 years since I had set a job on the machine for a VMC, and it felt good to know the craft has not left my hands and getting them dirty while making parts still makes me happy! Samaachar samaapth :)
0:28

We have now fully commissioned the machine after a few hiccups related to an old dying hard drive in the machine PC (it had a 1 gb hard drive!!) could save the machine in the nick of time with the help of a fellow machining junkie who knew how to do it! But the real reason i am writing is that we successfully ran our first 3D program on it and that the program was written entirely using Claude !! I did it myself and it took me a few hours to get it going. The best part of using Claude was that I could ask it to use macros to write the program which meant i could control *all* variables in the program. And it ran like a charm! Rendered on the part a fine finish and a brilliant high to see the part come out better than expected! I set the job myself because I wanted to get a feel for the machine, its ways and how to work with it. It had been nearly 15 years since I had set a job on the machine for a VMC, and it felt good to know the craft has not left my hands and getting them dirty while making parts still makes me happy! Samaachar samaapth :)

Sanjeev

11,761 views • 5 months ago