Caleb Brooks

@fabiensnauwaert This is very interesting

This is not a video avatar. It's one still image, deformed live in the browser with WebGL. Lipsync, blinks, nods, eye contact: all computed in real time from the TTS timings I already store. No video generation, no streaming, no GPU. $0 per reply. Building it for gliglish

@gracia_vr @UnrealEngine the animation is very realistic

Gracia Plugin for @UnrealEngine is battle-tested and ready to go. It’s built to make 4DGS assets a native part of your Unreal scene, integrated with the engine’s lighting, compositing, and post-processing systems. Key features: • Real-time lighting (splat relighting) and shadows, including self-shadowing • Drag-and-drop 4DGS import with synchronized playback and transitions • Streaming playback of 4DGS assets • Depth compositing • Exposure matching and per-object splat blending • Sequencer and Movie Render Queue support Request access and a sample project / assets through the inquiry form on gracia.ai!

@thepoonam0914 @Fikarnot_Aditi happy birthday

@Fikarnot_Aditi Happy Birthday aditi 🫶

Today my birthday 🎈

@abir35627 thank for sharing

50 USEFUL GITHUB REPOS 1. iFixAi — AI misalignment testing → github.com/ifixai-ai/iFix 2. public-apis — free APIs for everything → github.com/public-apis/pu… 3. build-your-own-x — learn by building → github.com/codecrafters-i… 4. developer-roadmap — learn any tech skill → github.com/kamranahmedse/… 5. free-programming-books — thousands of free books → github.com/EbookFoundatio… 6. system-design-primer → github.com/donnemartin/sy… 7. coding-interview-university → github.com/jwasham/coding… 8. the-art-of-command-line → github.com/jlevy/the-art-… 9. project-based-learning → github.com/practical-tuto… 10. you-dont-know-js → github.com/getify/You-Don… 11. the-book-of-secret-knowledge → github.com/trimstray/the-… 12. tech-interview-handbook → github.com/yangshun/tech-… 13. awesome-selfhosted → github.com/awesome-selfho… 14. javascript-algorithms → github.com/trekhleb/javas… 15. 30-seconds-of-code → github.com/Chalarangelo/3… 16. github gitignore templates → github.com/github/gitigno… 17. ollama — run LLMs locally → github.com/ollama/ollama 18. langchain → github.com/langchain-ai/l… 19. n8n automation → github.com/n8n-io/n8n 20. openclaw — local AI assistant → github.com/openclaw/openc… 21. dify — AI app builder → github.com/langgenius/dify 22. langflow → github.com/langflow-ai/la… 23. mem0 — AI memory layer → github.com/mem0ai/mem0 24. browser-use → github.com/browser-use/br… 25. crewAI → github.com/crewAIInc/crew… 26. MetaGPT → github.com/geekan/MetaGPT 27. AutoGen (Microsoft) → github.com/microsoft/auto… 28. aider — AI coding assistant → github.com/Aider-AI/aider 29. markitdown (Microsoft) → github.com/microsoft/mark… 30. open-webui → github.com/open-webui/ope… 31. maigret — OSINT tool → github.com/soxoj/maigret 32. TradingAgents → github.com/TauricResearch… 33. stagehand → github.com/browserbase/st… 34. firecrawl → github.com/mendableai/fir… 35. transformers (HuggingFace) → github.com/huggingface/tr… 36. vLLM → github.com/vllm-project/v… 37. llama.cpp → github.com/ggml-org/llama… 38. llama_index → github.com/run-llama/llam… 39. nanoGPT (Karpathy) → github.com/karpathy/nanoG… 40. RAGFlow → github.com/infiniflow/rag… 41. supermemory → github.com/supermemoryai/… 42. awesome-claude-skills → github.com/ComposioHQ/awe… 43. Bumblebee (Perplexity AI security tool) → github.com/perplexityai/b… 44. ComfyUI → github.com/comfyanonymous… 45. DeepSeek (official repo varies by model release) → github.com/deepseek-ai 46. Lobe Chat → github.com/lobehub/lobe-c… 47. freeCodeCamp → github.com/freeCodeCamp/f… 48. system design + interview prep extras (bonus) → github.com/jwasham/coding… 49. AI agents ecosystem (extra) → github.com/langchain-ai/l… 50. automation + AI workflows (extra) → github.com/n8n-io/n8n Save this before you forget it exists. You'll come back to at least ten of these.

@ventry089 it's very useful tools thanks for sharing

A dev quoted me two weeks to rebuild a landing page i loved. an AI agent did it before my coffee went cold. not a mockup. not a figma. the actual next.js code - fonts, animations, every section. EVERY WEBSITE JUST BECAME OPEN SOURCE everyone hoards "design inspo" screenshots they never open again. wrong game. the play isn't collecting sites you like - it's ripping them open. /clone-website + a URL, and a swarm of agents reverse-engineers the site in front of you: - exact colors, fonts, spacing - pulled as design tokens, not eyeballed - one builder agent per section, each in its own git worktree, all in parallel - visual diff against the original when they're done - runs on claude code + 12 other coding agents ai-website-cloner-template. 25k★ in 3 months. honest minus: heavy JS sites come out rough. and shipping a 1:1 clone is a lawsuit, not a shortcut - study it, remix it, ship your own. the loudest repo in my list of 102. the other 101 👇

@RetroChainer Mind-blowing hustle. One $47 AI camera + YOLO11 turned foot traffic counting into $11k/month passive income. Smart, simple, and scalable. No employees, no clipboard nonsense.Time to set this up on my street.

A 20-YEAR-OLD WANTED TO OPEN A BUSINESS BUT DIDN'T KNOW IF THE SPOT GOT ANY FOOT TRAFFIC. HE POINTED A $47 AI AT THE STREET, AND NOW 6 BUSINESSES PAY HIM $11,000 A MONTH. he didn't hire a market-research firm. he pointed a webcam at the sidewalk and let it count. the model boxes every person, car, and bag on screen and labels it. one frame, dozens of objects, 40 milliseconds. yolo11 already knows 80 things out of the box. person, car, bike, truck, dog. no training, no phd, no gpu farm. bytetrack gives each person one id, so it counts them once as they cross the line, not once per frame. the count lands in a csv, a streamlit dashboard shows it live, he sends the client a login. he wasn't selling code. he was selling one number: how many. the foot traffic he wanted for himself, every shop, gym, lot and cafe on that street wanted too. they were all still counting it by hand with a clipboard. month 1 was one parking lot at $500. month 6 was 6 clients at about $1,800 each. $11,000 a month, on $47 of tools he touches twice. no clipboard, no research firm, no employee standing at the door. the businesses on your street counted by hand today. they'll do it again tomorrow, unless someone shows up with the camera link. save this before someone on your street beats you to it.

@CCCSKB33 Impressive work! 1000 MetaHumans at Shibuya Scramble looks incredibly dense. Great to see the sample migration done smoothly. Excited for the model replacement tests in UE5.8! #UnrealEngine

#MetaHumanCrowd の確認。渋谷のスクランブル交差点で1000人発生させました。思ってたよりも大混雑。今回はサンプルをそのまま移行したので、次はモデル入れ替えの検証です。#UE5_8 #UnrealEngine #技術検証

@ltx_io thanks for sharing

@j_smeaton99 it's very realistic

Seedance 2.0 Prompt: Main Subject: Young Chinese woman, early 20s. Natural appearance. Black hair loosely tied back with soft bangs and loose strands. Minimal makeup. Comfortable everyday summer clothing: faded cream sleeveless top, loose light-blue jeans, worn canvas sneakers. Consistent identity, clothing, and appearance throughout. Location: Authentic rural Chinese village during a warm summer afternoon. Whitewashed walls, grey tiled roofs, narrow stone paths, vegetable gardens, bamboo baskets, clay pots, citrus trees, hanging laundry, old wooden gates, chickens occasionally wandering nearby. No modern commercial elements. Camera Style (Critical) Early-2000s consumer DV camcorder. Friend or family member casually filming. Heavy handheld shake. Late reframing. Frequent autofocus hunting. Lens breathing. Exposure pumping when moving between sunlight and shade. Slight motion blur. Rolling shutter. Digital compression artifacts. Soft detail. Slightly faded colors. Low contrast. Mild sensor noise. No stabilization. No cinematic grading. 00:00–00:02 The camera follows her entering through an old wooden courtyard gate. She spots her grandmother watering vegetables and immediately smiles. The camera clips the edge of the gate slightly while entering. Autofocus struggles to switch from the gate to her face. 00:02–00:04 Grandmother waters a small vegetable garden. The young woman walks over and takes the watering can for a moment. They exchange a few casual words and laugh naturally. The camera briefly focuses on tomato plants instead of them. 00:04–00:06 Near the garden. Grandmother points toward something growing among the vegetables. The young woman crouches to inspect it. Wind moves leaves and loose hair strands. Exposure shifts as clouds pass overhead. 00:06–00:08 In the courtyard. Grandmother hands her a freshly peeled orange segment. She takes a bite and smiles. The operator catches the moment slightly late. Camera drifts off-center. 00:08–00:10 They fold laundry together beside a clothesline. Fabric moves gently in the summer breeze. The camera briefly loses focus and hunts between hanging clothes and faces. 00:10–00:12 Sitting together on small stools in the shade. Grandmother says something amusing. The young woman laughs and lightly leans toward her. The shot feels completely unplanned and natural. 00:12–00:15 The young woman leaves through the courtyard gate carrying a small bag of fruit. Halfway down the path she turns back. Her grandmother is still standing there watching. They exchange one final wave. The camera zooms slightly, loses focus for a moment, then recording cuts off abruptly mid-motion. Audio Birds. Distant village sounds. Wind through trees. Rustling leaves. Laundry fluttering. Chickens. Footsteps on stone. Quiet family conversation. No music. No narration. Goal A forgotten family camcorder recording from the early 2000s. Warm, authentic, deeply nostalgic, emotionally universal, and completely believable.

@PythonHub Nice release! Baidu’s Unlimited-OCR uses Reference Sliding Window Attention on top of DeepSeek-OCR to parse entire multi-page documents in one shot with constant memory. Great for long PDFs without chunking. MIT licensed and open-source — worth testing.

Unlimited-OCR Unlimited-OCR is Baidu’s open-source OCR model for one-shot long-horizon document parsing, designed to read multi-page documents in a single pass instead of chunking them. github.com/baidu/Unlimite…

@MustafyOf Generating a full 3D walkthrough of a dream home is next-level. Definitely sharing that prompt—can't wait to try it myself.

Claude Fable is INSANE. It just made me a full 3D walk through of our dream home! Here's the prompt if you want to try it! 👇

@israfill this is very valuable

Alibaba open-sourced a script that embeds an AI agent into any webpage and kills browser automation as we know it 😳 one HTML tag. no headless browser. no Python. no Selenium. Page-Agent by Alibaba just hit 22K GitHub stars (+949 in a day). It is a JavaScript library that lives inside the webpage. reads the live DOM as structured text. acts as the real user. no computer vision. no multi-modal. just the DOM. what you get for $0: → drop one > configure your LLM (API key + model) > done - every page gets an AI copilot that understands it important: → accuracy depends on DOM cleanliness. highly dynamic SPA sites may need tuning → sends DOM content to whichever LLM you configure - keep sensitive data in mind → best for internal tools, admin panels, legacy systems → 22K stars, MIT, Alibaba open source → npm install page-agent also available for production apps your team spends months building internal tool UIs and maintaining browser tests you get an AI agent that controls any webpage with one line of HTML bookmark this before your next legacy system upgrade

@panahilang it's very execited

INCREDIBLE

@Strength04_X this is very realistic

The solitude of the sun and the sea 🌊 Made with Kling AI 3.0 Turbo

Hello, everyone. I collaborate with software companies in the United States and am looking for an experienced NA/EU-based software engineer to join me as a business partner. The opportunity offers competitive earning potential and long-term collaboration.

What is the future of AI?

HIRING (GLOBALLY)Fully remote. I’m looking for a Personal Assistant for a fully remote position. Also hiring for: • Document typing •Social media creation •logo design Experience Level: Any level (Beginners welcome) Budget: $1100-$1500

@bry_playz I'm interested. DM. I want the job.

Hey guys i’m looking for devs for my Roblox game look in the comments for more information #roblox #robloxdev #dev #developer #robloxdeveloper

@CodeMak_ I can everything you want. You can confirm my skill in this link. pulseboard-silk.vercel.app luminaanalytics.vercel.app

Looking for developer for one of my website. Any recommendation?

@Im_IrushiK I agree. I want it. email:caleb.brooks@gmail.com

Hiring nowadays: “We’re looking for a junior developer with the experience of a senior developer for the salary of an intern.” Agree or painfully agree?