Rahul Kumar

Je ba se ba!

[Rahul Kumar @wowool]

@sidhant @grok is that correct?

[Rahul Kumar @wowool]

@hilbertspaess And you didn’t know that this will happen!

[Rahul Kumar @wowool]

@AsFoundX A future version of Grok. No other human can do it.

[Rahul Kumar @wowool]

https://t.co/44VPY29c3I

[Rahul Kumar @wowool]

Models | Try NVIDIA NIM APIs https://t.co/WA3kCWDMSp

[Rahul Kumar @wowool]

@jk_rowling Good that you left the clue here on X, just in case… :-)

[Amy Mek @AmyMek]

Be a chainbreaker - Dad’s are everything ❤️

[Kirill @kirillk_web3]

A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone.

most people are still building agents the way that's about to be obsolete.

> why single-agent loops break and go "goal blind"
> the 4 parts of a graph: nodes, edges, state, policy
> 3 topologies that run everything: diamond, supervisor, pipeline
> Anthropic's 5 official workflow patterns

the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors.

I broke the same architecture down with Kimi K3. Full A-Z guide below.

[Amazes Mix @AmazesMix]

الفرق بين كريستيانو رونالدو وكثير من نجوم العالم في تعامله مع الأطفال المعجبين به… الأخلاق والإنسانية قبل كرة القدم ❤

[The Best @TheBestqueenx]

When an engineer designs a scarecrow.

[Rahul Kumar @wowool]

@Polymarket See it even has a Ferrari logo on all sides, so that you wouldn’t mistake it for a Citroën.

[Rahul Kumar @wowool]

@DefiantLs He says it’s Physics! I think he believes he is still that physicist from Marvel universe. Someone should wake him up.

[Rahul Kumar @wowool]

Tyson used to be an inspirational thinker, now he just embarrasses himself.

[Joe Rogan Podcast News @joeroganhq]

Neil deGrasse Tyson: "Elon Musk hasn't done anything that NASA hasn't already done."

[Rahul Kumar @wowool]

Make them stop walking like Joe Biden!

[Teslaconomics @Teslaconomics]

Bro… it’s 2026. You still clean your own room?

[Kanika @KanikaBK]

ANDREJ KARPATHY DESCRIBED THE PERFECT AI KNOWLEDGE SYSTEM.

Someone built it inside Obsidian. Claude Code x Obsidian. Under 10 minutes to set up.

YOUR VAULT WRITES AND ORGANIZES ITSELF while you sleep. Based on Karpathy's own LLM Wiki pattern. FREE.

Here is what is going on.
Everyone who uses Obsidian knows the problem. Notes go in. Connections never get made. Six months later you have hundreds of orphaned files, zero cross-references, and a second brain that feels more like a digital junk drawer. The system only works if you maintain it. Nobody maintains it.
This solves that entirely.

It is called claude-obsidian. You clone it, run one setup script, open it in Obsidian, type /wiki in Claude Code, and from that point forward Claude does all the organizing, filing, cross-referencing, and maintenance. You just drop things in and ask questions.

What makes it different from every other Obsidian AI plugin is this. Other plugins answer questions about your existing notes. This one creates, organizes, evolves, and maintains the notes autonomously. There is a difference between a chat interface and a knowledge engine.

↳ drop any source and Claude creates 8 to 15 structured wiki pages automatically
↳ every new page gets cross-referenced against everything already in the vault
↳ contradictions get flagged with callouts so you always know when sources disagree
↳ /autoresearch runs a 3 round web research loop, finds gaps, fills them, files everything
↳ /save turns any Claude conversation directly into a permanent wiki note
↳ hot cache updates every session so Claude never needs you to re-explain context again
↳ lint command finds orphans, dead links, and stale claims without you touching anything

The hot cache is the part most people miss. At the end of every session Claude writes a compact summary of recent context. Next session it reads that first. You never waste 10 minutes rebuilding context again.

10 skills. Multi-agent support. MIT license. Free forever.

[Maliha Tasnim @this_is_tasnim]

🚨 BREAKING: Someone just made OpenAI's Whisper transcribe 2.5 hours of audio in 98 seconds. 100% OPEN SOURCE.

It runs entirely on your GPU. No API keys. No cloud. No subscription.

It's called Insanely Fast Whisper.

You drop in an audio file. One command. You come back, and there's a clean, timestamped transcript waiting. Not a rough draft. Not a partial output. The entire thing. Done.

Not a wrapper.
Not a web app.

A CLI that turns your local machine into a transcription engine that makes paid services look embarrassing.

Here's what it does on its own:
→ Transcribes 150 minutes of audio in under 98 seconds using Flash Attention 2, same model, 19x faster, zero quality loss
→ Auto-detects language across dozens of languages, or translates directly into English with a single flag
→ Speaker diarization built in, knows who said what, not just what was said
→ Word-level and chunk-level timestamps so you can jump to any exact moment in any recording
→ Runs on NVIDIA GPUs and Apple Silicon Macs with zero code changes between them
→ Works on Google Colab free tier if you don't own a GPU at all

Here's how fast it actually is:

Standard Whisper large-v3 out of the box: 31 minutes to process 2.5 hours of audio. The same model with Flash Attention 2 and batching: 1 minute 38 seconds. Same weights. Same accuracy. One flag difference.

Here's the wildest part:
This never started as a product. It was a benchmark demo to show what Hugging Face Transformers could do. Then the community started using it for real work. Podcast transcription. Legal recordings. Research interviews. Meeting notes at scale. The team kept adding what people actually needed until a benchmark became a full CLI that nobody planned to build.

8.8K GitHub stars. 100% Open Source.