Cerebro: a librarian for the 463-exabyte-a-day internet
You missed a miracle while you slept. Between midnight and breakfast people uploaded five hundred hours of video every single minute. That is seven hundred and twenty thousand fresh hours in one day, enough footage to keep you watching until 2107 if you pressed play right now. And that is only YouTube. IDC says humanity will push out about 463 exabytes of new data every day in 2025. Stack that on hard drives and the column reaches the Moon and comes halfway back. Insane right? it get's worst. McKinsey finds that knowledge workers already burn a full work-day each week just hunting for…
What it does
In the maker’s words, at launch
You missed a miracle while you slept. Between midnight and breakfast people uploaded five hundred hours of video every single minute. That is seven hundred and twenty thousand fresh hours in one day, enough footage to keep you watching until 2107 if you pressed play right now. And that is only YouTube. IDC says humanity will push out about 463 exabytes of new data every day in 2025. Stack that on hard drives and the column reaches the Moon and comes halfway back. Insane right? it get's worst. McKinsey finds that knowledge workers already burn a full work-day each week just hunting for information they have created or paid for. Now bring AI into the picture. Europol’s analysts warn that up to ninety percent of everything you read online could be machine-generated by 2026. The models will write, then quote themselves, then train on the quotation. Noise that amplifies itself. Why should you care? Because the next time you need a fact whether to build, vote, or treat a fever you’ll have to dig it out of a an exponential wave of information that is still rising. Yesterday one reliable page could tilt the odds for anyone lucky enough to find it, today the same page is buried under a billion noise or masked by fake data and social proof. If we cannot tell signal from chatter we stop trusting anything. Research stalls, democracy wobbles, and every decision takes longer. Knowledge once tasted like power. Now it tastes like sand. What I am trying I am building Cerebro. Think of it as a librarian, not a factory. It ingests the PDFs, videos, and papers you care about. It verifies statements against originals before they reach your eyeballs. It maps concepts so you see only what changes the decision in front of you. No summaries that hallucinate. No extra content to clog the pipe. Just a shield that separates fact from filler. Version 0.1 is live for dog-fooding and every commit happens in public. Why bother telling you? Because if this resonates then you are exactly the person who can break it, improve it, or tell me it is the wrong fight. Questions for HN Which metric tells you that you have crossed from curiosity into overload? Where do existing curators fail you? If one slice of your reading workflow could be automated today what would you pick? I will be in the comments all day.
Does the same job
all alternatives →
- DTDownload the first 10,002,378 HN comments/stories as one archive2015 · ▲90
Magnet link: magnet:?xt=urn:btih:44c65b5779d9d8021e002584fa73740f36d052a6&dn=10m_hn_comments_sorted Go to https://hn-archive.appspot.com/ for the torrent file / source code. I'll be semi-frequently checking the story and answering any questions which may come up.
- ZRZFS+Rsync = Time Machine in the cloud2011 · blog.strongspace.com · ▲16
- LTListen to 3min clips of daily tech news stories instead of reading them2024 · lavalamp.ai · ▲5
I struggle with wanting to read heaps of stuff I come across on the internet daily, as well as being subscribed to a bunch of tech-related newsletters that I never get around to reading. I made this to get through that content much faster while working or otherwise multitasking. Check it out and please lmk your thoughts! Also, curious if others also feel this pain of too much interesting content to get through daily. FWIW I probably listen to this for >1 hour daily atm.
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 28d ago · voiceos.com
The New Calendly▲211Handle all of the work before, during, and after meetings
Work · 17d ago · calendly.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
