Prasoon Singh

Data Scientist @United | Aviation | GenAI

[Shubham Saboo @Saboo_Shubham_]

This is INSANE.

Google just dropped a free AI voice dictation app for iOS and Mac.

Every premium feature works without any subscription.

100% free, runs fully local, powered by Gemma 4.

[Movez @0xMovez]

Jane Street AI Engineer revealed how they trained their own LLM for trading to make $22.5B/year

16 minutes. free. straight from tier-1 quants.

bookmark & watch - this is the most honest "AI inside a hedge fund" talk ever published.

forget the "AI trading bot" YouTube grifters. This is the real inside view: data, training, evals, integration.

then start building your own bot using post below.

[Dilum Sanjaya @DilumSanjaya]

Fun interactive science app ideas | Part 3

Played around with generating 3D biological structures and made an app to explore them interactively

UI Design
GPT Images 2

Code
Gemini 3.1 Pro

More demos ↓

[el.cine @EHuanglu]

AI storytelling is crazy now

chatgpt image 2 can turn any story idea into storyboard with cast design.. then feed it to seedance 2 to get a full film scene.. this workflow is crazy on arcads

step by step tutorial with prompts:

[How To AI @HowToAI_]

China open-sourced a desktop automation agent that runs 100% locally.

It sees your screen, controls your mouse and keyboard, and completes tasks in any app through natural language.

100% Open Source. 29k stars on GitHub.

[How To AI @HowToAI_]

Someone just open-sourced a Claude Code skill that reverse-engineers any website.

Give it a URL and it screenshots the site, extracts every font and color, downloads all the assets, and rebuilds the whole thing pixel-perfect.

100% Open Source.

[Simplifying AI @simplifyinAI]

Someone just open-sourced the entire ElevenLabs + Descript stack in one tool.

It's called Voice-Pro. Zero-shot voice cloning, Whisper transcription, YouTube downloading, vocal isolation, and dubbing in 100+ languages.

All running locally in one Gradio WebUI.

100% Open Source.

[Movez @0xMovez]

This 30-min workshop by the creator of Claude Code will teach you more about vibe-coding than 100 YouTube video guides.

Bookmark it & give it 30 minutes today. This video will change the way you use Claude forever.

[Ai With Piyas @piyascode9]

🚨BREAKING: PowerPoint is officially outdated.

Claude can now create your full presentation in minutes — start to finish.

Here are 6 powerful prompts to do it all in one go.

(Save this & skip PowerPoint forever) 👇🏽

[Rimsha Bhardwaj @heyrimsha]

SOMEONE GOT TIRED OF PAYING HIGGSFIELD AI'S SUBSCRIPTION SO HE REBUILT THE WHOLE THING AND OPEN-SOURCED IT

200+ models. text-to-image, image-to-image, text-to-video, image-to-video all in one interface

you configure a virtual camera in the Cinema Studio. pick the body, the lens, the focal length, the aperture

and it writes the optimized cinematic prompt for you. completely in the background

you never touch the camera keywords. you just set up the shot like a real cinematographer would

Kling v3, Sora 2, Veo 3, Flux Dev, Midjourney v7, GPT-4o, Seedream 5.0, Runway Gen-3 all in there

self-hosted. MIT licensed. runs on your machine. your data stays local

the only thing you pay for is the model API calls themselves

someone built this so you never have to pay Higgsfield AI again

https://t.co/rw7gmAdW6X

[Ben Dicken @BenjDicken]

*Finally* read through @samwhoo's blog on LLM quantization.

It's incredible.

For many (even in tech) the understanding of how LLMs work stops at the surface level. Sam is helping us all go deeper, digging into the interesting facets of how AI models truly work.

Read it!

[Khairallah AL-Awady @eng_khairallah1]

🚨 BREAKING: Andrej Karpathy said someone should build this. 48 hours later it appeared on GitHub. For free.

It's called Graphify.

Bookmark it for later.

Karpathy keeps a /raw folder where he drops papers, tweets, screenshots, and notes. He called for a real product to turn that chaos into structured knowledge. Someone answered.

One command. Any folder. Full knowledge graph.

/graphify ./raw

What comes out:

→ An interactive knowledge graph you can click, search, and filter by community
→ A plain-language report with god nodes, surprising connections, and suggested questions
→ An Obsidian vault with backlinked articles (opt-in)
→ A wiki starting at index.md that any agent can navigate

The number that matters: 71.5x fewer tokens per query vs reading raw files. On a mixed corpus of repos, papers, and images, average query cost dropped from ~123K tokens to ~1.7K.

That is not optimization. That is a different paradigm for how AI reasons over large codebases.

Fully multimodal. Code in 19 languages via tree-sitter AST. PDFs. Images via Claude Vision. Screenshots, diagrams, whiteboard photos. Everything goes into one graph.

No vector database. No embeddings. Leiden community detection finds clusters by edge density. The graph topology is the similarity signal.

Auto-syncs as your codebase changes. Git hooks rebuild the graph after every commit and branch switch. SHA256 cache means re-runs only process changed files.

Works with Claude Code, Codex, OpenCode, OpenClaw, and Factory Droid.

pip install graphify && graphify install

MIT License. 100% Opensource.

(Link in the comments)

[How To AI @HowToAI_]

🚨 BREAKING: Someone just built a web-based System Design Simulator.

It's called Paperdraw. It lets you drag and drop components to see how they handle real-world conditions like traffic, failures, latency, and scaling in real time.

100% free to try.

[Simplifying AI @simplifyinAI]

🚨 BREAKING: Someone just built a tool that generates and visualizes complex 3d particle systems just by typing a prompt.

You tell it what you want, it builds the physics, and you export the react or three.js code instantly.

100% Free.

[Akshay 🚀 @akshay_pachaar]

How to setup your Claude code project?

TL;DR

Most developers skip the setup and just start prompting. That's the mistake.

A proper Claude Code project lives inside a .���𝗹𝗮𝘂𝗱𝗲/ folder. Start with 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 as Claude's instruction manual. Split it into a 𝗿𝘂𝗹𝗲𝘀/ folder as it grows. Add 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀/ for repeatable workflows, 𝘀𝗸𝗶𝗹𝗹𝘀/ for context-triggered automation, and 𝗮𝗴𝗲𝗻𝘁𝘀/ for isolated subagents. Lock down permissions in 𝘀𝗲𝘁𝘁𝗶𝗻𝗴𝘀.𝗷𝘀𝗼𝗻.

There are two .𝗰𝗹𝗮𝘂𝗱𝗲/ folders: one committed with your repo, one global at ~/.𝗰𝗹𝗮𝘂𝗱𝗲/ for personal preferences and auto-memory across projects.

The .𝗰𝗹𝗮𝘂𝗱𝗲/ folder is infrastructure. Treat it like one.

The article below is a complete guide to 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱, custom commands, skills, agents, and permissions, and how to set them up properly.

[Aiden Bai @aidenybai]

Introducing React Grab

Select any element on your page → tell Claude Code or Codex what to change

Fully open source

npx react-grab@latest

[Hasan Toor @hasantoxr]

🚨BREAKING: The "Ollama for voice cloning" just dropped.

It's called Voicebox and it clones any voice from just a few seconds of audio entirely on your machine.

No ElevenLabs subscription. No cloud uploads. No voice data leaving your device.

It's powered by Qwen3-TTS, Alibaba's breakthrough voice model.

→ Upload a few seconds of audio
→ Get a near-perfect voice clone
→ Generate speech in any language
→ Mix multi-voice conversations in a DAW-like timeline editor

All running locally. Zero cloud dependency.

But it's not just a TTS wrapper.

It's a full voice production studio:

→ Multi-track timeline editor for podcasts and dialogues
→ System audio capture + Whisper transcription built in
→ Voice prompt caching for instant regeneration
→ Built with Tauri (Rust), not Electron 10x smaller, native performance

100% Opensource. MIT Licensed.

macOS + Windows available now. Linux coming soon.

This is the moment voice cloning leaves the cloud and runs on your desktop.

Link in the first comment.

[Matt Shumer @mattshumer_]

https://t.co/ivXRKXJvQg