Brooks Whale X 🐋's banner

Brooks Whale X 🐋

@BrooksWhaleX • 38,267 subscribers

Everyone is talking about AI. I'm the one actually testing it. DM for collabs 📩 [email protected]

Shorts

🚨 CHINA JUST OPEN SOURCED AN OCR THAT EATS 100 PAGE PDFS IN ONE PASS It’s called Unlimited OCR. Only 3B params. Runs locally. Every other OCR tool chops your doc into pages and loses the thread. This one reads the whole thing in one continuous pass. → One shot full context parsing (32K context window) → Multilingual out of the box → 93% on the standard parsing benchmark (6 points over baseline) → Under 0.11 error rate past 40 pages → Runs 100% locally on your own hardware → Works with Transformers, vLLM, SGLang, Docker, Ollama, llama.cpp Traditional cloud OCR (Textract, Google Vision, Azure Doc Intelligence) costs $1.50 to $15 per 1,000 pages. This runs on your machine. For free. Forever. Baidu built it explicitly to push DeepSeek OCR one step further. Already at 1.9M downloads on Hugging Face and most people have no idea it exists yet. 100% open source.

🚨 CHINA JUST OPEN SOURCED AN OCR THAT EATS 100 PAGE PDFS IN ONE PASS It’s called Unlimited OCR. Only 3B params. Runs locally. Every other OCR tool chops your doc into pages and loses the thread. This one reads the whole thing in one continuous pass. → One shot full context parsing (32K context window) → Multilingual out of the box → 93% on the standard parsing benchmark (6 points over baseline) → Under 0.11 error rate past 40 pages → Runs 100% locally on your own hardware → Works with Transformers, vLLM, SGLang, Docker, Ollama, llama.cpp Traditional cloud OCR (Textract, Google Vision, Azure Doc Intelligence) costs $1.50 to $15 per 1,000 pages. This runs on your machine. For free. Forever. Baidu built it explicitly to push DeepSeek OCR one step further. Already at 1.9M downloads on Hugging Face and most people have no idea it exists yet. 100% open source.

486,370 views

🚨CONTENT CREATORS ARE SLEEPING ON THIS. Most AI video tools can generate videos. But turning a trending football story into a ready-to-post short is a different challenge. So I tested HeyGen's Avatar Shorts feature to see how much of the workflow it could automate. The result surprised me.

67,596 views

This is one generation. No retouch, no upscaler, no cleanup pass. Look at the eyes, the catchlight, the lashes, the bit of moisture. That's the stuff that usually outs an ai shot, and at 4k it just sits there holding up. Enterprises and Developers can access the official API via BytePlus, and you can also use it directly on BytePlus Lumina. BytePlus Lumina

This is one generation. No retouch, no upscaler, no cleanup pass. Look at the eyes, the catchlight, the lashes, the bit of moisture. That's the stuff that usually outs an ai shot, and at 4k it just sits there holding up. Enterprises and Developers can access the official API via BytePlus, and you can also use it directly on BytePlus Lumina. BytePlus Lumina

11,232 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

You’re late to the Apple Event. So you parkour your way in. #AppleEvent is hours away. We imagined the keynote opening like an action movie. No set. No stunt team. Just an idea turned into a cinematic sequence with Flova AI. Not a leak. Not official. Just our AI generated take on Apple’s biggest night. 👀 Made with FlovaAI

You’re late to the Apple Event. So you parkour your way in. #AppleEvent is hours away. We imagined the keynote opening like an action movie. No set. No stunt team. Just an idea turned into a cinematic sequence with Flova AI. Not a leak. Not official. Just our AI generated take on Apple’s biggest night. 👀 Made with FlovaAI

Brooks Whale X 🐋

57,455 views • 1 month ago

You're bleeding 10+ hours a week into content you could absorb in 120 seconds. Podcasts. Meetings. YouTube rabbit holes. Voice memos nobody asked for. You're still consuming all of it the slow, painful, outdated way. I stopped. Cold. Here's the switch I made: 🧵

You're bleeding 10+ hours a week into content you could absorb in 120 seconds. Podcasts. Meetings. YouTube rabbit holes. Voice memos nobody asked for. You're still consuming all of it the slow, painful, outdated way. I stopped. Cold. Here's the switch I made: 🧵

Brooks Whale X 🐋

60,446 views • 4 months ago

🚨 Video production agencies are going to hate this. I uploaded a deck to HeyGen and it came back as a corporate looking presentation video with a real avatar narrating every slide. No editing. No screen recording. No presenter. Just uploaded and it was done.🧵

Brooks Whale X 🐋

46,806 views • 4 months ago

THE BARRIER BETWEEN A PHOTO AND A VIDEO NO LONGER EXISTS AND HEYGEN JUST PROVED IT. I uploaded a photo to HeyGen, and it came back as a video. I genuinely did not expect that to work. But it did. And now every photo in my camera roll is potential video content.

THE BARRIER BETWEEN A PHOTO AND A VIDEO NO LONGER EXISTS AND HEYGEN JUST PROVED IT. I uploaded a photo to HeyGen, and it came back as a video. I genuinely did not expect that to work. But it did. And now every photo in my camera roll is potential video content.

Brooks Whale X 🐋

34,644 views • 4 months ago

After months of using HeyGen, I can say that it is the tool that has revolutionized my life the most. I used to cancel recordings all the time. Lighting wasn't right. Background was a mess. Some days I just didn't feel like showing up on camera. Then I found HeyGen's Avatar feature. I recorded myself once. I haven't cancelled since.

Brooks Whale X 🐋

23,813 views • 4 months ago

I wasted months re-explaining the same PDFs to ChatGPT every single session. Upload. Explain. Close tab. Repeat from zero. Found something that actually remembers. And my whole research workflow changed overnight 👇

I wasted months re-explaining the same PDFs to ChatGPT every single session. Upload. Explain. Close tab. Repeat from zero. Found something that actually remembers. And my whole research workflow changed overnight 👇

Brooks Whale X 🐋

19,467 views • 4 months ago

🚨 A Ukrainian developer just dropped a brilliant productivity hack that’s equal parts genius and hilarious. He built a GLSL shader for the Ghostty terminal that turns your screen into a living black hole. The longer you code without a break, the more it grows — warping and stretching your code with realistic gravitational lensing effects. Step away for a proper break? It shrinks back down, giving your text (and your brain) some breathing room. It’s a clever, visual reminder that even the best of us need to disconnect sometimes. Who knew astrophysics could make you more productive? Props to the creator, this is coding culture at its finest. (Repo in the comment)

🚨 A Ukrainian developer just dropped a brilliant productivity hack that’s equal parts genius and hilarious. He built a GLSL shader for the Ghostty terminal that turns your screen into a living black hole. The longer you code without a break, the more it grows — warping and stretching your code with realistic gravitational lensing effects. Step away for a proper break? It shrinks back down, giving your text (and your brain) some breathing room. It’s a clever, visual reminder that even the best of us need to disconnect sometimes. Who knew astrophysics could make you more productive? Props to the creator, this is coding culture at its finest. (Repo in the comment)

Brooks Whale X 🐋

14,751 views • 3 months ago

No more content to load