aizk

The key thing I realized is now I understand why github's infra struggled so much lately.

You're an order of magnitude too high.

I modeled the UI explicitly after tiktok and youtube shorts on desktop.

For wikitok, I made it take up the entire screen, but for this project I felt that having the comments was a core part of the experience so it's better to have them both side by side to get context, so the mobile-like layout wins.

I don't think that'll take off

It depends on how much usage it gets and the demand for changes. I updated wikitok for well over a month after it went viral because people were requesting changes. Then it found a sort of homeostasis point and now I rarely update it, because there just aren't as many requests.

I'm just here to make a fun little website to pass the time it's not that deep.

Ah, I only tested on a macbook and mobile. Will check that out.

Bought it before launching :) I learned my lesson from wikitok lol https://wikihack.org/

PS: If you liked this -- check out my https://www.wikitok.io/

Inspired by your site, I built out https://wikihack.netlify.app/

Hackerbooks, but for wikipedia :)

I hope you enjoy it.

I wonder if plain JS will make a comeback with how good AIs are at writing code (at least for one off simple sites)

Nitpick, maybe adding the youtube dislike counter estimation for videos might be a nice touch (yes it's an estimate but it's pretty decent). Though on second thought, perhaps these videos don't need them.

What a wonderful day for open source models.

Shivers (the original developer) sold it to them.

Sci fi has us thinking agent swarms act like savvy, terminator bots but they really just scream to me panicked middle managers trying to survive an audit.

If you're like me and also eager for cool uses for git, I'll share a cool one I use -- try out git for your resume! Commits change as you progress in life, and make branches for individually tailored resumes.

Blew my mind when I realized I could do that.

I can talk about this personally.

A year ago somebody make a page for wikitok, my 15 minutes of fame website. About a year after that, the user was banned for mass creating articles, allegedly. The article was then nominated to be deleted, because of the nature of the creator being banned for AI generated slop. A little while later, the article was deleted just because nobody bothered to vouch for it, funny times.

When you think of something in wikipedia, you may associate it with longevity, archival... Not the case, just like the web, links rot, things change, people play games / politics. It's all the same!

Really missed calling it localpedia!

How? You can be vague if need be, I'm just a bit curious.

I actually did mean the latter in that instance.

Can you be a bit less strange?

If you don't mind me asking -- what do you do for a living where you're just off buying an new car and a house in Japan?

Anime fans permeating throughout on the internet? Impossible. Never heard of such a thing.

Serious question -- how?

See here https://news.ycombinator.com/item?id=50135410

Caveat: I get a budget of free ai tokens at work, as I work for an open source AI inference provider.

My goal is to reverse engineer an entire gamecube game -- I'm pushing an existing community decomp that was stalled to the finish line, solo, with lots of AI help.

This work was directly inspired by https://decomp.dev/ -- which has just shut down a few days ago because of, ironically... people like me who enjoy decompiling things with AI, so I'm still weighing / grappling with the ethics of how to release my work, it's murky waters at best.

I use Opus 5.5 as the orchestrator, as well pi harness because it's somewhat lightweight. But for the really hard functions I don't use deepseek I use opus managing other opus agents.

I'm working to release something soon as proof that I can do a 100% decompilation job, but the main idea is that when decompiling a gamecube game your sources of truths are individual functions or files, so you can build off that primitive.

Each ai gets a worktree, and a shared giant context file that's basically a record of every experiment that has happened. They're assigned tasks to essentially do as much as they possible can for each individual funciton. After about an hour claude uses a script to merge the work that's actually correct (verified by tooling that checks if the c goes to asm) and then there are usually 3 rounds of reviews by independent ais, because there will always be some slight mistakes. The techniques used as well as the mistakes the models make are recorded in the giant ledger. There's a bunch of random one off scripts such as stuff to clean up, and tools to make sure the agents don't accidentally google stuff / delete stuff / use too much space.

Claude steers the ship via ssh on my strong linux tower at home so it keeps my laptop nice and cool and at this point I just check in from time to time, I am basically a manager, and Claude has it's own workers.

Last point -- I don't know any c besides the basics, I've only been "coding" python / ts for a couple of years, but even then with the extreme strength of models the future is managing agentic swarms, so I'm leaning in as much as I can. I really see this as the future of large scale projects. For some people it's a mockery of decompilation, but, my goal is the finish line, not the journey.

As the zoomers say these days "Unstoppable scroll vs unskippable title"

I use Opus 5.5 and swarms of about 50 deepseek models to reverse engineer old videos games. The scale is roughly 600k loc generated from pure asm, simply by knowing what the old compiler is. Truly staggering stuff.