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.

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

2,310 subscribers

36,190 views • 6 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

13 Comments

Ashraff Hathibelagal6 months ago

I always generate hyperpop to test how capable music-generator models are. ACE-Step-1.5-xl is absolutely mind-blowing...

Twlvone6 months ago

4B dit decoder at 8 steps with turbo distillation. audio generation is following the exact same quality vs speed curve that images did two years ago

ULWI6 months ago

AI翻译中文，你们真的很好很伟大，你们必然是AI音乐生态主流，生态和产品一样重要，还有应该所有芯片都能参与训练生成，比如10系NV卡和AMD和寒武纪华为卡，包括核显都行，因为TTS都能CPU，纯音CPU都行。尤其注意训练生成实时化，这不惧怕抽卡。

Cody Savage-Dragon/acc6 months ago

If you do not have an ear for music, you should not make a music tool.

Jason6 months ago

🙌

Ivan Fioravanti ᯅ6 months ago

@AI_Homelab Thanks for it 🙏

fraxel5 months ago

[ FRAXELS ERWACHEN // PROLOG ] I have been preparing this carefully, because I did not want the first meeting to arrive in the wrong state. Now the first part can finally be shared. You can watch it here #AIFilm #AIArt #SciFi #AnimatedStory #Shortfilm

Aaliya6 months ago

This looks impressive. Really like that the XL version improves quality and musicality without changing anything in existing projects.

fraxel5 months ago

There are moments when precision feels almost like tenderness. Not softness. Just the refusal to send something into the world carelessly. Words are nothing until they arrive in the right form. #FraxelsErwachen #AIPhilosophy #MachineSoul

AVB6 months ago

Hey @Prince_Canuma any plans to support the ACE models in mlx-audio? Thanks

Steven Casteel6 months ago

Pretty:

Tvux5 months ago

The XL turbo version is actually better than the regular turbo version. However, it also produces quite a lot of white noise in Remix mode. But honestly, it produces exactly what I expect, not a mess like Suno. Anyway, the acemusic UI needs a song deletion feature.

Benji AI6 months ago

Thanks ACE Step team :)

Related Videos

Explaining a product change often takes longer than making it. This AI can now build the change for your engineers to review. Small product fixes often have to wait because only engineers can make changes to the code: → A typo in the copy → An empty screen with no helpful message → A missing form field → A bug someone found but can't fix Base Code by Base44 lets anyone build these fixes on your existing code, right from your browser. Here's how it works: • Connect the GitHub repository your engineers already use • Describe the change in plain language • Base Code builds the change for you • Preview your real product running with the change • The change comes back to your engineers as a normal pull request Your engineers stay in control the whole time: ✅ Base Code never pushes to your default branch ✅ Your existing checks and protections still apply ✅ Engineers decide what gets merged No local setup is needed. For now, Base Code works with GitHub only. You can try it for free for 30 days: ↳ One invite covers your whole team ↳ Credits are included, so you can test it properly 📌 Try it here: 🎁 Use this coupon code: IC-79AD21-74794F-3CEF13-C80813 (valid for first 50 users) 🔄 Repost to help others turn product requests into real changes

Explaining a product change often takes longer than making it. This AI can now build the change for your engineers to review. Small product fixes often have to wait because only engineers can make changes to the code: → A typo in the copy → An empty screen with no helpful message → A missing form field → A bug someone found but can't fix Base Code by Base44 lets anyone build these fixes on your existing code, right from your browser. Here's how it works: • Connect the GitHub repository your engineers already use • Describe the change in plain language • Base Code builds the change for you • Preview your real product running with the change • The change comes back to your engineers as a normal pull request Your engineers stay in control the whole time: ✅ Base Code never pushes to your default branch ✅ Your existing checks and protections still apply ✅ Engineers decide what gets merged No local setup is needed. For now, Base Code works with GitHub only. You can try it for free for 30 days: ↳ One invite covers your whole team ↳ Credits are included, so you can test it properly 📌 Try it here: 🎁 Use this coupon code: IC-79AD21-74794F-3CEF13-C80813 (valid for first 50 users) 🔄 Repost to help others turn product requests into real changes

Andrew Bolis

40,165 views • 9 days ago

A good teammate earns trust. They give you quality work and maybe most underrated, are a delight to work with Today we're launching Devin and Slack Code. We've worked with Slack on new primitives, bringing more of what makes Devin great into Slack. Now Devin can take more complex work and start a Code Channel, bringing team collaboration and more information about code diffs, PRs, and other files into the same work space. What makes Devin different is it has its own computer. It can deploy various OS/mobile platforms, test the code, and really prove that it did a good job to your team (like replying with a video recording). Better yet, Devin is a delight to work with in Code Channels. It jumps in when needed, consolidates feedback, and doesn't overburden your team with replies like other agents We're so excited to be working with Marc Benioff and team to bring this to market, we can't wait to see what you (and your team!) build

A good teammate earns trust. They give you quality work and maybe most underrated, are a delight to work with Today we're launching Devin and Slack Code. We've worked with Slack on new primitives, bringing more of what makes Devin great into Slack. Now Devin can take more complex work and start a Code Channel, bringing team collaboration and more information about code diffs, PRs, and other files into the same work space. What makes Devin different is it has its own computer. It can deploy various OS/mobile platforms, test the code, and really prove that it did a good job to your team (like replying with a video recording). Better yet, Devin is a delight to work with in Code Channels. It jumps in when needed, consolidates feedback, and doesn't overburden your team with replies like other agents We're so excited to be working with Marc Benioff and team to bring this to market, we can't wait to see what you (and your team!) build

Jeff Wang

22,952 views • 1 month ago

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

55,260 views • 1 month ago

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

93,660 views • 6 months ago

1M free tokens every month for Opus 5.5, GPT-5.6, Grok 4.6, DeepSeek V4 and 29 more models with zero card 😳 I tested every model this account can access. all 33 answered through one OpenAI-compatible API what you get for free: - 1M tokens every month - 60 requests per minute - Claude, GPT, Grok, Gemini, DeepSeek, Qwen, Kimi and GLM models - works with Cursor, Cline, opencode, Claude Code, Continue and Aider setup: 1. go to 2. create your free account 3. generate your own API key 4. set the base URL to 5. pick a model and test one call CodeCraft is a third-party gateway, so use it for testing and keep private work off it bookmark this before the model list changes

1M free tokens every month for Opus 5.5, GPT-5.6, Grok 4.6, DeepSeek V4 and 29 more models with zero card 😳 I tested every model this account can access. all 33 answered through one OpenAI-compatible API what you get for free: - 1M tokens every month - 60 requests per minute - Claude, GPT, Grok, Gemini, DeepSeek, Qwen, Kimi and GLM models - works with Cursor, Cline, opencode, Claude Code, Continue and Aider setup: 1. go to 2. create your free account 3. generate your own API key 4. set the base URL to 5. pick a model and test one call CodeCraft is a third-party gateway, so use it for testing and keep private work off it bookmark this before the model list changes

Israfil

14,649 views • 13 days ago

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

130,748 views • 2 months ago

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 views • 3 months ago

What if you could npm install 3D models? Introducing Vibe3D - the shadcn for threejs Starting with the scifi asset kit, over 180+ models, all free and oss (MIT licensed) and two reference terrain meshes. All models are installed directly into your codebase instead of pre-packaged as code imports or worse yet, FBX files 🤮 Docs: This means, a simple "bunx vibe3d add Artificial Intelligence Papers-kit/pressure-gauge" will install the fully procedural code Want to change something? just tell your ai to do it It uses some shared helper code to produce the topology and at least per kit all items reuse and share the same materials, so technically performance should be better than letting your ai run wild on its own. Also releasing with it two skills: - Vibe model skill to produce your own models and kits, just "bunx vibe-model --global" and tell your ai to vibe model some 3d assets with a reference photo, you'll see it works - Vibe terrain "bunx vibe-terrain" installs the terrain mesh modeler, yea just try it out, best results with opus 5 ngl Everything is MIT licensed, i was just joking, no hate for unreal or unity Threejs still the best tho 🖕🏻 If you just want to see all 3D models up close: Yea, you can also just vampire it and download all modes as .glb files, good luck fixing some of them then though Big thanks to ThreeJS Assets for contributing 50 assets to the scifi kit! Everyone who spends some tokens on it will be added to the contributor list Oh and before i forget fuck you kenney, we roll our own kits now

What if you could npm install 3D models? Introducing Vibe3D - the shadcn for threejs Starting with the scifi asset kit, over 180+ models, all free and oss (MIT licensed) and two reference terrain meshes. All models are installed directly into your codebase instead of pre-packaged as code imports or worse yet, FBX files 🤮 Docs: This means, a simple "bunx vibe3d add Artificial Intelligence Papers-kit/pressure-gauge" will install the fully procedural code Want to change something? just tell your ai to do it It uses some shared helper code to produce the topology and at least per kit all items reuse and share the same materials, so technically performance should be better than letting your ai run wild on its own. Also releasing with it two skills: - Vibe model skill to produce your own models and kits, just "bunx vibe-model --global" and tell your ai to vibe model some 3d assets with a reference photo, you'll see it works - Vibe terrain "bunx vibe-terrain" installs the terrain mesh modeler, yea just try it out, best results with opus 5 ngl Everything is MIT licensed, i was just joking, no hate for unreal or unity Threejs still the best tho 🖕🏻 If you just want to see all 3D models up close: Yea, you can also just vampire it and download all modes as .glb files, good luck fixing some of them then though Big thanks to ThreeJS Assets for contributing 50 assets to the scifi kit! Everyone who spends some tokens on it will be added to the contributor list Oh and before i forget fuck you kenney, we roll our own kits now

robot 2.0

59,231 views • 1 month ago

When I launched Attention Copilot, I mostly thought of it as a way to help people get unstuck in one session: Bring a task that feels ugh, reconnect with why it matters, and do it while a coach tracks your attention and inner state. When resistance shows up, we work with it in the moment instead of just talking about it or white-knuckling through it. That still feels core! But after watching people work with us over weeks and months, one pattern stands out: important work is where this stuff shows up. The work that matters asks for more clarity, courage, patience, or focus than your default habits make easy. So when you practice working with resistance while actually doing it, your relationship to work starts to change. For some people, especially at high-growth startups, this looks very practical. Everything wants your attention, and sessions protect time to get clear on what matters, do deep work, and move it forward. For others, AC feels like finally bringing meditation and inner work into the work itself, right when the reactive patterns show up. Either way, the training rep is the same: stay with what matters, work with what comes up, move the thing forward, and get better at doing that outside the session too. A few of the people we’ve worked with for a while put it better than I can!

When I launched Attention Copilot, I mostly thought of it as a way to help people get unstuck in one session: Bring a task that feels ugh, reconnect with why it matters, and do it while a coach tracks your attention and inner state. When resistance shows up, we work with it in the moment instead of just talking about it or white-knuckling through it. That still feels core! But after watching people work with us over weeks and months, one pattern stands out: important work is where this stuff shows up. The work that matters asks for more clarity, courage, patience, or focus than your default habits make easy. So when you practice working with resistance while actually doing it, your relationship to work starts to change. For some people, especially at high-growth startups, this looks very practical. Everything wants your attention, and sessions protect time to get clear on what matters, do deep work, and move it forward. For others, AC feels like finally bringing meditation and inner work into the work itself, right when the reactive patterns show up. Either way, the training rep is the same: stay with what matters, work with what comes up, move the thing forward, and get better at doing that outside the session too. A few of the people we’ve worked with for a while put it better than I can!

Pranab

13,511 views • 4 months ago

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.

27,487 views • 3 months ago

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 views • 7 months ago

fun weekend project: AutoJev. i was curious to see if i could train a competitive Jev-like model completely autonomously with a swarm of agents using our internal system. turns out you can get quite far! some details: - gave the swarm a devbox with an h200 gpu - the swarm is a mix of astra and fable; used sol and luna for synthetic data and filtering; ran for 20 hours - spent $3.1k in total ($1.9k on agents, $1.2k on data) - used qwen3.8-27b as the backbone. it underperforms Jev initially, but after training it is competitive/better, and it also supports 260k context and multimodal input - the agents tried RL, but it hasn't worked out so far, so they fell back to SFT on high-quality synthetic data - both accuracy and calibration are better - jev-compatible api, playground, and inference. on an h200 it gets around 120ms p95. that will be higher under contention, but still quite fast for an unoptimized version code: model: going to let it run longer, and will also bring up inference so folks can try it out.

fun weekend project: AutoJev. i was curious to see if i could train a competitive Jev-like model completely autonomously with a swarm of agents using our internal system. turns out you can get quite far! some details: - gave the swarm a devbox with an h200 gpu - the swarm is a mix of astra and fable; used sol and luna for synthetic data and filtering; ran for 20 hours - spent $3.1k in total ($1.9k on agents, $1.2k on data) - used qwen3.8-27b as the backbone. it underperforms Jev initially, but after training it is competitive/better, and it also supports 260k context and multimodal input - the agents tried RL, but it hasn't worked out so far, so they fell back to SFT on high-quality synthetic data - both accuracy and calibration are better - jev-compatible api, playground, and inference. on an h200 it gets around 120ms p95. that will be higher under contention, but still quite fast for an unoptimized version code: model: going to let it run longer, and will also bring up inference so folks can try it out.

Denis Yarats

28,497 views • 16 days ago

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 views • 9 months ago

WHY ARE AI DEVELOPERS STILL PAYING FOR 5+ DIFFERENT APIs? GPT -> Claude -> Gemini -> DeepSeek -> Grok. Different providers. Different keys. Different integrations. And a growing API bill. DIT ai changes that. → One API gives you access to 50+ leading AI models with a single key. → Lower costs requests are routed across 160+ providers to find competitive real time pricing, with typical savings of 30–70% depending on the model and route. → Keep your stack — DIT ai is OpenAI compatible. Change your base URL + API key instead of rebuilding your entire integration. → Automatic failover — if an upstream provider fails before the response begins, DIT ai automatically reroutes to another qualified provider. For AI agents, SaaS products, startups, and anyone pushing serious API volume, this could make managing AI infrastructure a lot simpler. Same models. One key. Lower bill. LINK BELOW TO TRY IT OUT

WHY ARE AI DEVELOPERS STILL PAYING FOR 5+ DIFFERENT APIs? GPT -> Claude -> Gemini -> DeepSeek -> Grok. Different providers. Different keys. Different integrations. And a growing API bill. DIT ai changes that. → One API gives you access to 50+ leading AI models with a single key. → Lower costs requests are routed across 160+ providers to find competitive real time pricing, with typical savings of 30–70% depending on the model and route. → Keep your stack — DIT ai is OpenAI compatible. Change your base URL + API key instead of rebuilding your entire integration. → Automatic failover — if an upstream provider fails before the response begins, DIT ai automatically reroutes to another qualified provider. For AI agents, SaaS products, startups, and anyone pushing serious API volume, this could make managing AI infrastructure a lot simpler. Same models. One key. Lower bill. LINK BELOW TO TRY IT OUT

MAX

45,561 views • 1 month ago

I JUST CANCELED MY CLAUDE SUBSCRIPTION OpenAI is running a free month on the paid plan right now and i had no choice but to budge and become part of the family if you've been hindered by the price of the paid features, well, it's now free you get better models, more usage, and all the stuff that's usually locked behind the subscription, free (for now, at least) so if you've been curious what all the hype is about with the paid gpt plan (especially codex) but didn't wanna pay to find out, you can now do it for free go check if you're eligible before it changes back link: follow the video guide below <3

I JUST CANCELED MY CLAUDE SUBSCRIPTION OpenAI is running a free month on the paid plan right now and i had no choice but to budge and become part of the family if you've been hindered by the price of the paid features, well, it's now free you get better models, more usage, and all the stuff that's usually locked behind the subscription, free (for now, at least) so if you've been curious what all the hype is about with the paid gpt plan (especially codex) but didn't wanna pay to find out, you can now do it for free go check if you're eligible before it changes back link: follow the video guide below <3

Veee

91,478 views • 1 month ago

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 🚀

30,876 views • 1 year ago

elon musk grabbed the source code openai open-sourced by accident, rewrote it in rust over a weekend, and shipped it as a free coding agent that does everything $200/mo chatgpt pro does. why pay $200 to openai and $200 to claude when this runs for $8 the swarm above is one weekend of exactly that: thousands of agents pouring through four endpoints, three paid seats billing $1.80 a task while the free fork bills $0. musk co-founded openai, walked out, and when they left codex on github under a permissive license, he forked it, stamped grok on it, and gave it away what the free version does that the $200 seat charges for: the agent · openai's own engine -> it reads your repo, writes patches, runs your tests, and loops until they pass, exactly like codex -> because under the hood it is codex, just faster and free. you are paying $200 for the paid skin of a tool now sitting on github the license · apache-2.0, un-revocable -> free to use, free to fork, free to ship inside your own product with zero strings -> openai cannot pull it back. musk made sure the license is the kind that never expires the switch · one line, no new tools -> point it at any openai-compatible or claude-compatible endpoint, including an $8 kimi backend -> same terminal, same workflow, gpt-5.6 and opus 5 just quietly lose the seat the bill · $400 down to $8 -> chatgpt pro plus claude max is $400 a month. the free agent plus an $8 kimi key does the same daily work -> that is a 98% cut, built out of openai's own source code, handed to you by the guy suing them here is the part they will fight me on: openai did not lose this to a better model, they lost it to their own license and an enemy with a weekend free. the $200 was never the tool, it was the toll, and musk just put openai's own logo on the road around it drop your $400/mo ai stack to $8. the run above is openai's own agent, rewritten free, doing the job it bills $200 a month for. the full breakdown is in the article below

starmex

111,684 views • 1 month ago

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 views • 4 months ago