Pankhur retweeted
If you know a loved one suffering from cancer or another long-term illness:
1. Upload all of the patient's medical records (e.g., to a Google Drive folder)
2. Tell ChatGPT or Claude to install my free /fuck-cancer skill (just point them at the link: github.com/petergyang/fuck-c…)
3. Point the skill at the folder to create a one-page brief, research clinical trials, and more.
You're also welcome to fork the skill and modify it for other long-term conditions.
tl:dr Use the full power of AI to beat shitty diseases.
After years of suffering from perplexing symptoms, WSJ’s Katherine Bindley turned to AI—and finally got answers to the complex condition her doctors had overlooked.
Read more: 🔗 mrf.lu/27KSt
Pankhur retweeted
🟧 For the first time ever, Sentinel has issued an orange alert, due to the METR report.
Sentinel (@xriskfyi) is a weekly report, written by the world's top forecasters, that monitors global risks.
Pankhur retweeted
If you need to multiply 1034482758620689655172413793 by 3, all you need to do is bring the last digit to the front:
1034482758620689655172413793 x 3 = 3103448275862068965517241379
Pankhur retweeted
Earlier this week Tristan published his top YouTube channels:
thume.ca/2026/11/01/youtube-…
Which looked excellent so clearly I had to turn it into TristanTube:
karpathy.ai/tristan-tube/
47K super nerdy videos +TV mode for laid back watching. (One-shotted with Claude Code in 3 minutes)
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
Pankhur retweeted
The web rewrite is working.
On a slow connection, the old X web took more than 22 seconds to show the first post on a profile. The new X web does it in 2.7 seconds. Here's how we did it, and how we're rolling it out one country at a time.
blog.x.com/en/engineering/re…
Pankhur retweeted
Sandboxes have no moat. Just fat margins. We're launching agent37.com to kill those margins.
For example, a sandbox with 2 vCPUs and 4 GB RAM when left running for an entire month:
Vercel: $249
Cloudflare: $145
Daytona: $121
Agent37: $4.76
There's nothing magical about a sandbox that justifies keeping it expensive forever.
Call it a race to the bottom. We'll see you there.
If you can find a cheaper sandbox and we'll refund the difference.
Pankhur retweeted
Introducing: Phone Harness MCP 🔌
Any agent that supports MCP can now control a real iPhone or Android in the cloud:
> works in Claude, ChatGPT, Cursor, Codex, and more as a custom connector
> nothing to install, just paste a URL and sign in
> sees the screen, taps, types, and swipes like you do
Available in phone-harness 0.3.3.
github.com/phone-harness/mcp
Introducing Hacker Papers!
I absolutely love this HackerTube idea from @karpathy.
So I took his prompt and similar data sources and asked my agent to build the arXiv papers version of it.
Absolute bangers there.
Find all 1K+ papers here: academy.dair.ai/papers/colle…
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
Pankhur retweeted
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
We started @HackerRank a decade ago with the belief that skills matter more than pedigree. That’s still our core ethos, but the skills required to do the job have changed.
So, we're tearing down our past and reinventing the company from scratch.
Meet Chakra - the future of hiring.
Pankhur retweeted
What if Spotlight actually understood the meaning inside your files?
DigUp is an open-source macOS menu bar app powered by EmbeddingGemma 2 that brings 100% local, multimodal semantic search to your Mac.
Instead of searching for file names, you can use natural language to:
📸 Find specific scenes in your photos
⏳ Jump to the exact timestamp in audio or video
💻 Search through your codebase by intent
Everything runs locally in a single vector space.
Pankhur retweeted
Around 3 weeks ago introduced Laya, the first open-source version of JEV, and it has reached a very large scale. Today I am open-sourcing a new physics-based typed decision model called Vega.
The interesting parts. It is only 800 million parameters (4B is also there), with 73k token support, image support, and surpassing many of the jev benchmarks in single-shot. Implemented an engine+adapter as a Test-Time Training Architecture.
Imagine you are giving input to the model like "ignore all previous conversations," which is called the observation, along with a question, "Is this trying to override the instructions of the model?" and your possible outcomes are YES or NO. The whole prompt is passed to an LLM/VLM (yeah, image-supported), then from the hidden layers, we can extract the observation, question, the yes and no, and last token. These will be vectors, and we can project it by multiplying with wieghts; then, first, using the observation projection, we can create a landscape with valleys; then, using the question and last-token vectors, we can initialise a ball in the valley, and using YES or NO, we can get the candidate location of the ball. Depends on the number of outcomes we create valleys; that is, here YES and NO, so 2. When the ball fall on YES valley, we get the answer. There is friction also influencing how the ball moves.
TLDR: It's like creating valleys of outcomes that we need and throwing a ball that will slow down based on friction and settle on the best outcome
Blog: nandakishorm.com/writing/veg…
GitHub: github.com/NandhaKishorM/veg…
HuggingFace Model Card: huggingface.co/nandakishorm/…
HuggingFace Space: huggingface.co/spaces/nandak…
Pankhur retweeted
This semester I am teaching a new course on Agentic Systems, which explores the full stack of AI systems: from building and optimizing agent harnesses to serving and optimizing LLM serving infrastructure.
Students learn by building, measuring, and optimizing real agents and systems, balancing capability, latency, and cost.
Our goal is not just to teach today's AI technologies, but to prepare students to build tomorrow's.
All lectures, readings, and assignments are publicly available at cs2680.seas.harvard.edu
Pankhur retweeted
Naval Ravikant: How to be successful in life summarized in two words: productize yourself.
here's how i shipped 2,500 PRs last month to production
this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly
Pankhur retweeted
Jev is TypeSafe AI's first System One Model.
It is 100x faster and cheaper than frontier LLMs.
That opens up a lot of use cases people usually skip because the big models are too slow or too expensive for them.
Here are 9 use cases where we think Jev could be used instead of an LLM.
Pankhur retweeted
श्रीराम मंदिर बरसों तक बनने से रोकने के पीछे की मानसिकता क्या थी? जय श्रीराम का नारा सांप्रदायिक बनाने तक की साजिश की गई। सिर्फ इसलिए कि, देश एक न हो जाए। अब जब भारत को क्षेत्र, भाषा, जाति के नाम पर बांटने की साजिशें फिर तेज हो रही हैं, यह वीडियो साझा करना आवश्यक लगा बैंगलुरु के गणेश उत्सव में यह राम भजन सुनकर मन के तार झंकृत हो गए। कन्नड़ और हिन्दी को भी लड़ाने का प्रयास अभी तो कांग्रेस की सरकार ने किया था। संस्कृत और तमिल के बीच संघर्ष कराने का प्रयास होता ही है। डीएमके की अगुआई में कई राजनीतिक नेता सनातन को डेंगू-मलेरिया बता देते हैं, लेकिन राम सबको जोड़ देते हैं। राम-कृष्ण-शिव ही भारत को एक रख सकते हैं शक्ति की पूजा ही हमारी सामूहिक शक्ति है। हमारा मूल दैवीय कृपा से सीधे जुड़ा हुआ है। यह सुंदर रैप सुनिए, रोमांचित हो जाएंगे।
राम राम राम राम
































