Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

ACE-Step-1.5-xl is out now. We scaled the DiT decoder to 4B. And it shows better audio quality, better prompt following, and better musicality. It still fast -- 8 steps with turbo distillation. What didn't change: - Same generation API, same LoRA training code, same everything - All LM models... show more

ACE Music

2,317 subscribers

35,886 Aufrufe • vor 4 Monaten •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I open-sourced my 3d towers building site and the skills I used to create well-textured three.js models. The entire site is 1.38mb gzipped, including all models, sounds and textures. Site: Github repo: Skills: - threejs-towers - threejs-weather - threejs-landscape With an open-source project you get a way better starting point. All you need is to ask what to change, how to improve it, and rebuild it for a different theme. I added Cambodia, Vietnam and Turkey, plus storms and blizzards, and those came out perfectly with one prompt. The foundation is done, so adapting it and pairing it with your taste is what takes it further. Try modern towers, different backgrounds, weather and styles. SimCity, Civilization, Warcraft, C&C, etc. It's really fun.

I open-sourced my 3d towers building site and the skills I used to create well-textured three.js models. The entire site is 1.38mb gzipped, including all models, sounds and textures. Site: Github repo: Skills: - threejs-towers - threejs-weather - threejs-landscape With an open-source project you get a way better starting point. All you need is to ask what to change, how to improve it, and rebuild it for a different theme. I added Cambodia, Vietnam and Turkey, plus storms and blizzards, and those came out perfectly with one prompt. The foundation is done, so adapting it and pairing it with your taste is what takes it further. Try modern towers, different backgrounds, weather and styles. SimCity, Civilization, Warcraft, C&C, etc. It's really fun.

Meng To

51,214 Aufrufe • vor 5 Tagen

SOMEONE MADE IT SO YOU CAN CODE WITH 174 AI MODELS FROM 23 PROVIDERS FOR FREE one npm package and one install: "npm i -g free-coding-models" switch between any model instantly. benchmark them against each other in real time to see which one actually codes best for your use case. no subscriptions. no API keys. no cost. 174 models. 23 providers, all free, all from your terminal. if you're tired of paying for 3 different AI subscriptions just to compare which model codes better, this is it

SOMEONE MADE IT SO YOU CAN CODE WITH 174 AI MODELS FROM 23 PROVIDERS FOR FREE one npm package and one install: "npm i -g free-coding-models" switch between any model instantly. benchmark them against each other in real time to see which one actually codes best for your use case. no subscriptions. no API keys. no cost. 174 models. 23 providers, all free, all from your terminal. if you're tired of paying for 3 different AI subscriptions just to compare which model codes better, this is it

Om Patel

86,969 Aufrufe • vor 4 Monaten

Most people judge AI models by what they can do today. rahul judges the slope. When we started Ramp, people had tasted better software at home and could no longer tolerate the tools they were handed at work. So we built something better. Same thing is happening now with AI. Our customers use these models every day. They know what speed and intelligence feel like — and anything that makes them repeat themselves or wait for an answer feels broken. Rahul builds for that. Not for the best model today, but for where models will be in 3–6 months. Studying traces. Improving the harness. Cutting CI time. Giving agents real work with real guardrails. He gets into all of it with Boris Cherny, Paul Jankura's Head of Claude Code, and our staff engineer Austin Ray.

Most people judge AI models by what they can do today. rahul judges the slope. When we started Ramp, people had tasted better software at home and could no longer tolerate the tools they were handed at work. So we built something better. Same thing is happening now with AI. Our customers use these models every day. They know what speed and intelligence feel like — and anything that makes them repeat themselves or wait for an answer feels broken. Rahul builds for that. Not for the best model today, but for where models will be in 3–6 months. Studying traces. Improving the harness. Cutting CI time. Giving agents real work with real guardrails. He gets into all of it with Boris Cherny, Paul Jankura's Head of Claude Code, and our staff engineer Austin Ray.

Karim Atiyeh

128,815 Aufrufe • vor 9 Tagen

Anthropic Engineer Andrej Karpathy: "Stop training from scratch. Take what the model already learned - adapt it - ship it At OpenAI we replaced months of work with a few lines of code. Better results every time " the Karpathy formula for working with AI: step 1 → stop building from zero. the model already learned the hard part - just point it at your task step 2 → stop adding complexity, the simplest architecture beat everything in 2014 - simpler always wins step 3 → train only the last layer and freeze everything else - minutes instead of months. better results he taught this at Stanford 10 years ago - then applied it at OpenAI, Tesla, and Anthropic the advice never changed - because it never stopped working watch - bookmark, then read article below ↓

Anthropic Engineer Andrej Karpathy: "Stop training from scratch. Take what the model already learned - adapt it - ship it At OpenAI we replaced months of work with a few lines of code. Better results every time " the Karpathy formula for working with AI: step 1 → stop building from zero. the model already learned the hard part - just point it at your task step 2 → stop adding complexity, the simplest architecture beat everything in 2014 - simpler always wins step 3 → train only the last layer and freeze everything else - minutes instead of months. better results he taught this at Stanford 10 years ago - then applied it at OpenAI, Tesla, and Anthropic the advice never changed - because it never stopped working watch - bookmark, then read article below ↓

codila

25,376 Aufrufe • vor 1 Monat

FREE DeepSeek V4 Pro and V4 Flash API. Runtime by Bad Theory Labs just dropped it. Same platform, new free model, same 2-minute setup. > Runtime already gave you free Claude Opus 4.8 and GPT 5.5 access. Now they added DeepSeek V4 Pro and V4 Flash to the free tier. Absolutely FREE, YES. Same exact flow as before: → Go to runtime(.)badtheorylabs(.)com → Sign up with Google → Fill in your details during onboarding → Free balance lands automatically(But you don't need it to use DeepSeek - it's completely free right now) → Grab your API key from the dashboard → Plug into OpenCode, OpenClaw, or Hermes - done DeepSeek V4 Pro is one of the strongest coding and reasoning models available right now. Free tier also includes btl-2 - auto-routes between GLM, OpenAI, Anthropic, and Gemma. 10 million tokens per month at zero cost. 344 models total. One OpenAI-compatible endpoint. No code rebuild, no card, no limits hunting. >> Just start using the API, and when choosing a provider, select DeepSeek I tested it myself - fully working. Bookmark this before the free tier fills up.

FREE DeepSeek V4 Pro and V4 Flash API. Runtime by Bad Theory Labs just dropped it. Same platform, new free model, same 2-minute setup. > Runtime already gave you free Claude Opus 4.8 and GPT 5.5 access. Now they added DeepSeek V4 Pro and V4 Flash to the free tier. Absolutely FREE, YES. Same exact flow as before: → Go to runtime(.)badtheorylabs(.)com → Sign up with Google → Fill in your details during onboarding → Free balance lands automatically(But you don't need it to use DeepSeek - it's completely free right now) → Grab your API key from the dashboard → Plug into OpenCode, OpenClaw, or Hermes - done DeepSeek V4 Pro is one of the strongest coding and reasoning models available right now. Free tier also includes btl-2 - auto-routes between GLM, OpenAI, Anthropic, and Gemma. 10 million tokens per month at zero cost. 344 models total. One OpenAI-compatible endpoint. No code rebuild, no card, no limits hunting. >> Just start using the API, and when choosing a provider, select DeepSeek I tested it myself - fully working. Bookmark this before the free tier fills up.

Atenov int.

26,920 Aufrufe • vor 1 Monat

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.

Sudo su

45,052 Aufrufe • vor 5 Monaten

The next generation of mobile apps will run multimodal AI locally by default. Today, we’re making it practical for developers to ship. We just launched NexaSDK for Mobile on Product Hunt. Developers can run the latest multimodal AI models fully on-device in iOS & Android apps with Apple Neural Engine and Qualcomm Hexagon NPU acceleration. In just 3 lines of code, build chat, multimodal, search, and audio features with no cloud cost, complete privacy, 2x faster speed and 9× better energy efficiency. Try out NexaSDK for Mobile and we’d love your feedback (Product Hunt link in thread).

The next generation of mobile apps will run multimodal AI locally by default. Today, we’re making it practical for developers to ship. We just launched NexaSDK for Mobile on Product Hunt. Developers can run the latest multimodal AI models fully on-device in iOS & Android apps with Apple Neural Engine and Qualcomm Hexagon NPU acceleration. In just 3 lines of code, build chat, multimodal, search, and audio features with no cloud cost, complete privacy, 2x faster speed and 9× better energy efficiency. Try out NexaSDK for Mobile and we’d love your feedback (Product Hunt link in thread).

NEXA AI

319,337 Aufrufe • vor 8 Monaten

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

Akshay 🚀

30,856 Aufrufe • vor 1 Jahr

I spent 3 minutes editing a video I would've reshoot for an entire day. Runway just dropped Aleph 2.0, and it's not another "generate from scratch" AI tool. It edits footage you already have. Here's what that actually means: - You type the change. One sentence. - It applies across the entire clip. Multi-shot sequences included. - Only what you asked changes. Background, lighting, and motion all untouched. - Preview before you commit. No blind generations. I tested it with a product color swap: same clip, different color, same everything else. The output looked like a separate shoot. For anyone running ads or producing content variants, this is the tool. One clip, multiple deliverables, zero reshoots. Live now → Code ALEPH2 = 22% off 2 months of Pro (till May 31) ⚡ #MadeWithRunway Runway #ad

I spent 3 minutes editing a video I would've reshoot for an entire day. Runway just dropped Aleph 2.0, and it's not another "generate from scratch" AI tool. It edits footage you already have. Here's what that actually means: - You type the change. One sentence. - It applies across the entire clip. Multi-shot sequences included. - Only what you asked changes. Background, lighting, and motion all untouched. - Preview before you commit. No blind generations. I tested it with a product color swap: same clip, different color, same everything else. The output looked like a separate shoot. For anyone running ads or producing content variants, this is the tool. One clip, multiple deliverables, zero reshoots. Live now → Code ALEPH2 = 22% off 2 months of Pro (till May 31) ⚡ #MadeWithRunway Runway #ad

CODIFY

40,843 Aufrufe • vor 2 Monaten

Zerve has been the best platform for writing data science code for a while. It's 100x better than Jupyter notebooks. Now, they have a specialized, fine-tuned AI assistant who knows all about data science code and how to use the platform. This is a killer feature. A generalist model will never be better than a specialized one. Watch the video. I promise you'll be jealous in 3 minutes. Some other features, in case you've never used Zerve: 1. It's web-based 2. You can share and work with your team on the same canvas 3. You can deploy your code with a click 4. Blocks are the center of attention. Promotes code modularity 5. You can combine multiple languages in a single canvas 6. You can run code blocks in parallel Zerve organizes your code as a DAG. Each block inherits the state of every block before it. Everything runs in a serverless architecture. By the way, you can use Zerve for FREE. Visit this link: Thanks to the team for partnering with me on this post.

Zerve has been the best platform for writing data science code for a while. It's 100x better than Jupyter notebooks. Now, they have a specialized, fine-tuned AI assistant who knows all about data science code and how to use the platform. This is a killer feature. A generalist model will never be better than a specialized one. Watch the video. I promise you'll be jealous in 3 minutes. Some other features, in case you've never used Zerve: 1. It's web-based 2. You can share and work with your team on the same canvas 3. You can deploy your code with a click 4. Blocks are the center of attention. Promotes code modularity 5. You can combine multiple languages in a single canvas 6. You can run code blocks in parallel Zerve organizes your code as a DAG. Each block inherits the state of every block before it. Everything runs in a serverless architecture. By the way, you can use Zerve for FREE. Visit this link: Thanks to the team for partnering with me on this post.

Santiago

27,942 Aufrufe • vor 1 Jahr

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

124,923 Aufrufe • vor 2 Monaten

𝗥𝘂𝗻 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗮𝘀 𝗮 𝗳𝗿𝗲𝗲 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗶𝗻 𝟯 𝘀𝘁𝗲𝗽𝘀. No API bills. No usage limits. No subscription. Nothing leaves your computer. Here's the full setup: → Step 1: Go to Download and install. Update to version 0.2.2.0 or higher. → Step 2: Open terminal. Type: ollama pull gemma4. Downloads the model. Done. → Step 3: Install OpenClaw. Select Ollama as your provider. Point it at port 11434. Pick Gemma 4. That's it. Your AI agent is now running locally. Message it through Telegram, Slack, Discord, or WhatsApp like a coworker. Read files. Write code. Remember context across every conversation. All on your own hardware. Gemma 4 ranked number 3 on the global open model leaderboard on launch day. It beat models with 20 times more parameters. The 26B version activates only 4B parameters at a time so you get near large-model quality at small-model speed. Every AI subscription you're paying for right now could be replaced with this.

𝗥𝘂𝗻 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗮𝘀 𝗮 𝗳𝗿𝗲𝗲 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗶𝗻 𝟯 𝘀𝘁𝗲𝗽𝘀. No API bills. No usage limits. No subscription. Nothing leaves your computer. Here's the full setup: → Step 1: Go to Download and install. Update to version 0.2.2.0 or higher. → Step 2: Open terminal. Type: ollama pull gemma4. Downloads the model. Done. → Step 3: Install OpenClaw. Select Ollama as your provider. Point it at port 11434. Pick Gemma 4. That's it. Your AI agent is now running locally. Message it through Telegram, Slack, Discord, or WhatsApp like a coworker. Read files. Write code. Remember context across every conversation. All on your own hardware. Gemma 4 ranked number 3 on the global open model leaderboard on launch day. It beat models with 20 times more parameters. The 26B version activates only 4B parameters at a time so you get near large-model quality at small-model speed. Every AI subscription you're paying for right now could be replaced with this.

Julian Goldie SEO

36,898 Aufrufe • vor 4 Monaten

Want your own custom AI helper? With upcoming updates from OptimAI, it's super simple! 🤖✨ Just type one sentence and the network does all the smart work behind the scenes: - Super-fast edge computing + private learning - Secure global storage - Real human feedback to make it better In 3 easy steps: ✅ Drop your prompt ✅ OptimAI finds/refines/trains everything ✅ Get your personal AI agent, ready to work & keep improving! Anyone can build powerful AI now The future of AI is here, and it's for everyone. 🚀

Want your own custom AI helper? With upcoming updates from OptimAI, it's super simple! 🤖✨ Just type one sentence and the network does all the smart work behind the scenes: - Super-fast edge computing + private learning - Secure global storage - Real human feedback to make it better In 3 easy steps: ✅ Drop your prompt ✅ OptimAI finds/refines/trains everything ✅ Get your personal AI agent, ready to work & keep improving! Anyone can build powerful AI now The future of AI is here, and it's for everyone. 🚀

OptimAI Network

15,714 Aufrufe • vor 4 Monaten

2 years ago, Riffusion was one of the first music generating AI models, by finetuning Stable Diffusion literally on images of waveforms, and then decoding those as audio again I made a song for my gf with it called "Bunny Trouble, Trouble Bubble" about a year ago, extremely catchy and we loved it But it was capped to 12 seconds and I could only imagine how it'd be as a full song Now Suno is finally good enough and I used it as an input so I could extend it from a 12 second clip to 3 minute song, it's essentially the audio version of img2img It took a few times extending it and half the times the output was very bad but the other half it was really great The quality is still a bit low because Riffusion's quality itself was quite low, so that's not Suno's fault, it just extends the low quality into a full song, what I need is an audio upscaler to fix that The fun thing about this, every year music generating AI will be better and I can try inputting the song again to make it better and better If you wanna do the same with your short clip: 1) go to Suno 2) click Create 3) click Custom 4) Upload Audio, upload your short clip here Your existing clip now gets added to the listing on the right (bit confusing) 5) Now hover over it and tap extend 6) More confusingly it will now only play the extended part not the full song 7) To get the full song, click the 3 vertical dots ... -> Create -> Get Whole Song 8) That will stitch your original input clip and the extended clip into one Now you'll probably have a 1 minute clip, so 9) Extend that WHOLE SONG clip again and do the same stitch thing (Get Whole Song) again Depending on the clips you like and not, choose the ones you wanna continue with by stitching them By now you'll have about a 3 minute song!

2 years ago, Riffusion was one of the first music generating AI models, by finetuning Stable Diffusion literally on images of waveforms, and then decoding those as audio again I made a song for my gf with it called "Bunny Trouble, Trouble Bubble" about a year ago, extremely catchy and we loved it But it was capped to 12 seconds and I could only imagine how it'd be as a full song Now Suno is finally good enough and I used it as an input so I could extend it from a 12 second clip to 3 minute song, it's essentially the audio version of img2img It took a few times extending it and half the times the output was very bad but the other half it was really great The quality is still a bit low because Riffusion's quality itself was quite low, so that's not Suno's fault, it just extends the low quality into a full song, what I need is an audio upscaler to fix that The fun thing about this, every year music generating AI will be better and I can try inputting the song again to make it better and better If you wanna do the same with your short clip: 1) go to Suno 2) click Create 3) click Custom 4) Upload Audio, upload your short clip here Your existing clip now gets added to the listing on the right (bit confusing) 5) Now hover over it and tap extend 6) More confusingly it will now only play the extended part not the full song 7) To get the full song, click the 3 vertical dots ... -> Create -> Get Whole Song 8) That will stitch your original input clip and the extended clip into one Now you'll probably have a 1 minute clip, so 9) Extend that WHOLE SONG clip again and do the same stitch thing (Get Whole Song) again Depending on the clips you like and not, choose the ones you wanna continue with by stitching them By now you'll have about a 3 minute song!

@levelsio

55,113 Aufrufe • vor 1 Jahr

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Kyle Hessling

24,481 Aufrufe • vor 2 Tagen

-> someone cloned claude -> design interface and -> made it completely free -> it's work on YouTube -> and also suitable for kids -> it’s called open design -> and it’s live on github -> same clean split-screen ui -> you get in claude artifacts -> prompt on the left, live -> design/code preview on -> the right, type what you -> want to build and it -> generates the ui in real -> time, but here’s the twist -> you pick the ai model -> not locked into one -> company, want to use -> gemini, mistral, llama, -> deepseek any model -> with an api work -> if you’re running local -> models with ollama -> that works too -> no subscription walls -> the big difference -> vs claude artifacts -> works with any free -> ai model you’re not -> paying $20/mo just to -> design, use free tiers -> local models, or whatever -> you already have access to -> fully local, your prompts -> and code never leave -> your machine unless -> you want them to -> no data training -> no cloud storage -> privacy by default -> no usage limits -> claude cuts you off -> after a few designs -> here you can generate, -> iterate, break things -> and rebuild all day -> the only limit is your -> don’t like how a button -> works, change it -> want to add your own -> components, go ahead -> you own the tool -> so if you’ve been gatekept -> by paywalls or worried -> about sensitive prompts -> going to some company’s -> servers, this fixes that. -> same workflow, more -> control, zero monthly fee

-> someone cloned claude -> design interface and -> made it completely free -> it's work on YouTube -> and also suitable for kids -> it’s called open design -> and it’s live on github -> same clean split-screen ui -> you get in claude artifacts -> prompt on the left, live -> design/code preview on -> the right, type what you -> want to build and it -> generates the ui in real -> time, but here’s the twist -> you pick the ai model -> not locked into one -> company, want to use -> gemini, mistral, llama, -> deepseek any model -> with an api work -> if you’re running local -> models with ollama -> that works too -> no subscription walls -> the big difference -> vs claude artifacts -> works with any free -> ai model you’re not -> paying $20/mo just to -> design, use free tiers -> local models, or whatever -> you already have access to -> fully local, your prompts -> and code never leave -> your machine unless -> you want them to -> no data training -> no cloud storage -> privacy by default -> no usage limits -> claude cuts you off -> after a few designs -> here you can generate, -> iterate, break things -> and rebuild all day -> the only limit is your -> don’t like how a button -> works, change it -> want to add your own -> components, go ahead -> you own the tool -> so if you’ve been gatekept -> by paywalls or worried -> about sensitive prompts -> going to some company’s -> servers, this fixes that. -> same workflow, more -> control, zero monthly fee

BeingInvested

12,134 Aufrufe • vor 2 Monaten

This just cracked the internet…🥚 She runs to Target to grab her usual organic eggs; same brand, same label she normally buys at Sprouts Farmers Market. No big deal, right? Until she cracks one open… Bright yellow yolk. Not the rich orange she’s used to; this looks completely different. Same carton. Same “organic” label. But side-by-side? They don’t even look like the same product. Now she’s spiraling, are they fake? is it quality? what are we actually paying for? And honestly… people are starting to question everything. When the same “premium” product looks completely different depending on where you buy it… something feels off. Does yolk color actually mean better quality, or have we all been fooled by marketing this whole time? Would YOU still eat them?

Dr. CZ

143,233 Aufrufe • vor 4 Monaten

AI is extremely good at spending your money very quietly. our own token spend went from a rounding error to more than 10% of payroll in a year. one week in May we burned through $1.5 m. our CFO didn't love telling me that number, and he really didn't love telling the internet. but every finance leader we talk to is living the same story. the bill keeps going up and teams can't answer basic questions about it. which team is driving it? which models they're using? what changed this month? whether a cheaper model would do the same job? so finance gets two bad options: keep paying and hope, or cut broadly and slow down the work that's actually compounding. we built a third one. Ramp now connects to OpenAI, Anthropic, Gemini, Cursor and pulls it all into one place. see it, understand it, control it - down to a single API key. built with 1,000+ companies managing 100T+ tokens a month, and now spending less than they expected too! try it today at

AI is extremely good at spending your money very quietly. our own token spend went from a rounding error to more than 10% of payroll in a year. one week in May we burned through $1.5 m. our CFO didn't love telling me that number, and he really didn't love telling the internet. but every finance leader we talk to is living the same story. the bill keeps going up and teams can't answer basic questions about it. which team is driving it? which models they're using? what changed this month? whether a cheaper model would do the same job? so finance gets two bad options: keep paying and hope, or cut broadly and slow down the work that's actually compounding. we built a third one. Ramp now connects to OpenAI, Anthropic, Gemini, Cursor and pulls it all into one place. see it, understand it, control it - down to a single API key. built with 1,000+ companies managing 100T+ tokens a month, and now spending less than they expected too! try it today at

Eric Glyman

331,555 Aufrufe • vor 1 Monat