Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

DeepSeek-V4.1-Flash is crazy! first time experiencing a model this FAST that’s also this efficient this is what I built in less than a minute with just a simple prompt in Alysis Code

0xRemakw's profile picture

remakw

1,833 subscribers

20,153 Aufrufe • vor 18 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

This model is insane at landing pages. I asked DeepSeek V4.1 Flash & Claude Fable 5 to build me a landing page for a movie theater. Fable cost $1.21 while V4.1 Flash cost 2.6 cents, making it more than 40x cheaper at similar quality. Gave both the exact same prompt!
0:11

This model is insane at landing pages. I asked DeepSeek V4.1 Flash & Claude Fable 5 to build me a landing page for a movie theater. Fable cost $1.21 while V4.1 Flash cost 2.6 cents, making it more than 40x cheaper at similar quality. Gave both the exact same prompt!

Hassan

55,618 Aufrufe • vor 15 Tagen

This is surreal. I just played a video game that’s actually a neural network. No code backing this thing. Just model weights. Keyboard inputs come in, frames come out. New computing era.
0:15

This is surreal. I just played a video game that’s actually a neural network. No code backing this thing. Just model weights. Keyboard inputs come in, frames come out. New computing era.

n@alie

12,806 Aufrufe • vor 1 Jahr

This is insane! 🤯 Just built a new skill in Claude Code using Opus 4.5. The skill uses Gemini 3 Pro (via API) for designing web pages. Look at what it generated from one simple prompt.
0:11

This is insane! 🤯 Just built a new skill in Claude Code using Opus 4.5. The skill uses Gemini 3 Pro (via API) for designing web pages. Look at what it generated from one simple prompt.

elvis

152,981 Aufrufe • vor 10 Monaten

Minimax H3 by MiniMax Design (H3) is crazy good. With just a single line prompt, Heisenberg and Jesse are back in the lab but this time, they’re cooking up flawless code. 🧪💻
0:13

Minimax H3 by MiniMax Design (H3) is crazy good. With just a single line prompt, Heisenberg and Jesse are back in the lab but this time, they’re cooking up flawless code. 🧪💻

Heisenberg

23,671 Aufrufe • vor 1 Monat

Mia Khalifa & Michael Scott A job interview from The Office, but with… Sorry, guys—I just had to do this 🤣🤣🤣 I created this entire video on MiniMax Design (H3) using MiniMax H3—with just a single prompt. This model is absolutely insane. I’ve been running a lot of tests, and I honestly haven’t had this much fun with a model in a very long time.
0:14

Mia Khalifa & Michael Scott A job interview from The Office, but with… Sorry, guys—I just had to do this 🤣🤣🤣 I created this entire video on MiniMax Design (H3) using MiniMax H3—with just a single prompt. This model is absolutely insane. I’ve been running a lot of tests, and I honestly haven’t had this much fun with a model in a very long time.

Riccardo Wolf

21,355 Aufrufe • vor 1 Monat

DeepSeek V4 Flash 0731 first test. DeepSeek V4 Flash 0731 is ridiculously cheap compared to Kimi K3, GPT-5.6, and Opus 5 For its price, this is a surprisingly capable model. First challenge: Generate a railway station in Three.js. The result exceeded my expectations for such a low-cost model. It’s definitely one to watch if you’re building 3D projects on a tight budget.
0:15

DeepSeek V4 Flash 0731 first test. DeepSeek V4 Flash 0731 is ridiculously cheap compared to Kimi K3, GPT-5.6, and Opus 5 For its price, this is a surprisingly capable model. First challenge: Generate a railway station in Three.js. The result exceeded my expectations for such a low-cost model. It’s definitely one to watch if you’re building 3D projects on a tight budget.

FHILY👑

21,825 Aufrufe • vor 1 Monat

A line in AI video was crossed, in my experiments with just the web interface, H3 Max can now create reasonably high quality AI video in less time than it takes you to watch it. This is realtime from the moment I pushed the "generate" button (and also includes prompt enhancement)
0:17

A line in AI video was crossed, in my experiments with just the web interface, H3 Max can now create reasonably high quality AI video in less time than it takes you to watch it. This is realtime from the moment I pushed the "generate" button (and also includes prompt enhancement)

Ethan Mollick

89,671 Aufrufe • vor 29 Tagen

kling 3.0 is crazy... this model works very different than any other model this is from giving it just 2 images and a multi prompt then it handled all the scenes by itself... now imagine what it could do if you gave it more references and an even more detailed multi prompt going to test this a lot more but kling definetly cooked on this one
0:12

kling 3.0 is crazy... this model works very different than any other model this is from giving it just 2 images and a multi prompt then it handled all the scenes by itself... now imagine what it could do if you gave it more references and an even more detailed multi prompt going to test this a lot more but kling definetly cooked on this one

Miko

95,977 Aufrufe • vor 7 Monaten

this is what 14 hours of GPT-Astra in Unreal Engine looks like. gave it a simple prompt: build a scene of Superman returning to Earth, like in Zack Snyder’s Batman v Superman. this is probably the best output I’ve seen from this model so far. AGI is here.
0:14

this is what 14 hours of GPT-Astra in Unreal Engine looks like. gave it a simple prompt: build a scene of Superman returning to Earth, like in Zack Snyder’s Batman v Superman. this is probably the best output I’ve seen from this model so far. AGI is here.

Veee

41,173 Aufrufe • vor 20 Tagen

After playing with the Jev hybrid model, I started looking into OpenJev, and started with a halite 1 implementation with: GLM 5.3 Flash + Jev [vs] GLM 5.3 Flash + OpenJev OpenJev is just a 4B model handily defeating Jev (in this tiny silly toy example ofc). Now I'm super curious to learn what Jev's actual model size is.
0:13

After playing with the Jev hybrid model, I started looking into OpenJev, and started with a halite 1 implementation with: GLM 5.3 Flash + Jev [vs] GLM 5.3 Flash + OpenJev OpenJev is just a 4B model handily defeating Jev (in this tiny silly toy example ofc). Now I'm super curious to learn what Jev's actual model size is.

Harrison Kinsley

24,797 Aufrufe • vor 4 Tagen

what if Claude could work for you and change your life in less than 1 minute what if a new life was just 1 prompt away something new is coming to clawpump
0:10

what if Claude could work for you and change your life in less than 1 minute what if a new life was just 1 prompt away something new is coming to clawpump

clawpump

29,484 Aufrufe • vor 7 Monaten

this is not a joke... An AI just built a LinkedIn clone (but less cringe). with nothing but text prompts. No code, no design skills, no dev team burning $200K salaries. this is just one of 10 wild examples: 👇
0:14

this is not a joke... An AI just built a LinkedIn clone (but less cringe). with nothing but text prompts. No code, no design skills, no dev team burning $200K salaries. this is just one of 10 wild examples: 👇

Shruti

38,740 Aufrufe • vor 1 Jahr

this is it I quit trading Fable 5 has built a 100% winrate trading strategy in less than 420 minutes I am not going to share this, don't even ask
0:13

this is it I quit trading Fable 5 has built a 100% winrate trading strategy in less than 420 minutes I am not going to share this, don't even ask

Stoic Trader

100,219 Aufrufe • vor 2 Monaten

Grok Build is a beast. Built this Animated 3D Website with 1 Prompt Prompt 👇
0:10

Grok Build is a beast. Built this Animated 3D Website with 1 Prompt Prompt 👇

Viktor Oddy

16,898 Aufrufe • vor 3 Monaten

omg... Google's Opal is really GOOD. You can now build mini apps with just a single prompt I built this idea to infographic app using Opal in just 2 minutes!👇
0:14

omg... Google's Opal is really GOOD. You can now build mini apps with just a single prompt I built this idea to infographic app using Opal in just 2 minutes!👇

Poonam Soni

40,338 Aufrufe • vor 8 Monaten