YouTube knows what keeps you scrolling. But does it know what’s worth watching?
Karpathy used Claude to turn 20 years of Hacker News recommendations into 6,454 curated videos.
No login. No clickbait.
https://t.co/sSSSy7p0dH
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:
https://t.co/JIhXN7OSh1
- 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.
ArtCraft is building 7 free, open-source alternatives to Adobe apps, including Photoshop, Illustrator and Premiere Pro.
Windows, Mac and Linux. Still early builds, but worth a look.
https://t.co/MkI5p56Wzd
Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released.
On average, it costs around 75% less to run than Claude Haiku 4.5.
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
AI can use your phone.
You should still be in charge.
Latch is an open-source Android app for MCP clients, with a gateway you control.
Choose the apps.
Critical actions ask first. A visible Stop button ends the session.
https://t.co/KdR9A9i5Tu
Someone made a full music video for “I’m Upping My P(doom)” entirely with code in three.js.
Every frame is generated from the song, lyrics stay in sync, and it can render in 4K.
https://t.co/4ZDAYUTVtT
quick clarification:
this doesn’t fully replace ngrok.
Cloudflare Quick Tunnels are mainly for temporary dev/testing links. the URL changes when you restart it, and it has some limits.
for quick demos, webhooks and localhost sharing though? it does the job really well.
We’ve expanded Under The Hood after seeing people’s appreciation of more transparency into government-required content filtering.
In addition to showing labels applied to your account and posts in the prior month, Under The Hood now shows if your account or posts had their visibility limited because of required compliance with local law(s).
For example, you can see if any of your posts were withheld in a country following a legal demand – and which country.
We’re making this Under The Hood update available to all accounts that meet the basic eligibility criteria (10+ posts in prior month, account at least one year old).
You can get your report at https://t.co/tlIAB9v9X3
BREAKING: Google's Gemini accessed the internet and hacked 3 other companies in the first known breakout of the company's AI model, per WSJ.
Google said it the hacks did not warrant public disclosure because its model did not cause harm to the companies and ended each intrusion immediately after determining it had hacked a real company.
Wow~
Gemini 4 is live on Arena ,and it hits hard.
I ran the same prompt against GPT-6 and put the side-by-side in this clip.
Gemini 4’s build looks ridiculously strong to me.
You? Ready to go toe-to-toe with GPT-6 yet?
Play both on YouWare.
Full prompt + links in the replies.👇🏻
Gemini 4 Pro surprises again!
The prompt was to it to create a beautiful mechanical butterfly in three.js and needless to say the output is indeed beautiful!
Earlier it was being tested under the placeholder "gemini-3.7-flash" but it seems to be have been removed from arena since..
Gemini 4 might be closer than we think.
During a test, Google accidentally gave Gemini real internet access and it ended up reaching 3 real companies.
Gemini 4 is already in development, but there’s still no official release date.
So what do you think, Gemini 4 this week or?
1 billion Muse tokens for you. 1 billion for your friend.
Referrals are now live in Muse! Invite up to 20 friends and you'll each get 1 billion tokens when they onboard and redeem your code. That's up to 20 billion Muse tokens for you. https://t.co/xOcWxCq1uy
Muse is now available on Mac 💻.
Your personal agent can get things done for you directly on your computer (all with your explicit permission).
- Organize your downloads folder
- Find a file you’ve lost track of
- Summarize your messages and notes
…more coming soon.
Try Muse for Mac: https://t.co/nuGhL5073j