sudo jajos
309 subscribers
111 photos
14 videos
92 links
$ sudo jajos --verbose

Junior AI Engineer@iCogLabs|Oriental Orthodox|Just fascinated about anything fascinating ๐Ÿ˜

Will share my thoughts and journey here
Download Telegram
Been quiet for a while โ€” not idle though. Got a lot cooking. But yeah, I think I'm back. I'll be posting about my journey โ€” learning new things, building, and just the real ups and downs of thriving in tech, especially AI.
๐Ÿ‘Œ3
Hi fans ๐Ÿ™Œ

been diving into continual learning lately and honestly... it's fascinating ๐Ÿง 

basically the problem is โ€” how do you teach a model new stuff without it forgetting everything it already knows? turns out it's really hard lol

found this paper on sparse memory finetuning and the approach is kinda crazy. instead of updating the whole model (which wrecks it), you give it millions of tiny memory slots and only touch the relevant ones. like... surgical precision ๐Ÿ”ฌ

the numbers: full finetuning forgets 89%. LoRA still forgets 71%. this method? only 11%. that's wild

still early research (1.3B scale) but the direction feels right. this is where always-learning AI actually starts to look possible

also I started google's nested learning path a while back but never finished it... getting back to that too ๐Ÿ˜…

https://jessylin.com/2025/10/20/continual-learning/
so... I've been working on something ๐Ÿ‘€

building an AI learning playground โ€” basically a place where you can actually learn AI by doing, not just watching tutorials and reading papers all day

especially heavy on reinforcement learning ๐ŸŽฎ โ€” training agents, reward shaping, policy stuff... RL is one of those things that clicks 10x faster when you see an agent actually learn in real time vs staring at equations

it's still super early stages but I'll be sharing progress here regularly. this channel is basically the build log now ๐Ÿ› 

oh and โ€” if there's a topic you want me to cover or break down, drop it in the comments or slide into my DMs ๐Ÿ’ฌ I'm building this for y'all so lmk what you actually want to learn

I will include things I want to learn meaning I will be building them while learning that thing

stay tune
๐Ÿ”ฅ4
I will be using this kinds of templates whenever I post -> I kinda like them ... maybe we could have another persona than the hacker like this one, maybe ... like minimalistic hand drawings ...
๐Ÿ‘2
Me wasting my time ๐Ÿ˜ nevermind ๐Ÿ˜

Was thinking about what to use for post images on this channel.

Then thought โ€” what if I just build it myself?
A bunch of templates I can pick from, type my text, export.

So that's what I did.

SJ Studio โ€” a canvas engine that renders post graphics.
8 styles. 20+ templates. All pure Canvas 2D, no design tools.

Terminal, Glass, Glitch, Gradient, Notebook,
Blueprint, Node Graph, Polaroid.

Mostly an internal tool for the channel.
Not trying to build a startup out of it.

But it's open source โ€” if you want to use it, use it.
Want to contribute a template or style? PRs welcome.

github.com/jajos12/sj-studio -> give it starts if u like it

https://sj-studio-gamma.vercel.app/

I don't really know if it is useful or not frankly ๐Ÿ˜

#buildinpublic
๐Ÿ‘1๐Ÿซก1
You know I love game dev but I hadn't pursued it because u can't be all where all at once ๐Ÿ˜ (which is exactly what we all devs try to do ๐Ÿ˜)-> but at some moment maybe no far I want to vibe code a good game ๐ŸŽฒ ...
๐Ÿ˜1
sudo jajos
You know I love game dev but I hadn't pursued it because u can't be all where all at once ๐Ÿ˜ (which is exactly what we all devs try to do ๐Ÿ˜)-> but at some moment maybe no far I want to vibe code a good game ๐ŸŽฒ ...
Ofc it wouldn't be tic tac toe or x/o -> I think of like an rpg game maybe or ๐Ÿค” some kind of platformers ... also sandbox games maybe ...
๐Ÿ‘1
๐Ÿ‘1
sudo jajos
Photo
Remember when I said I wanted to vibe code a game?

I did it. One session. Start to finish. (I mean we did it ๐Ÿ˜, I think u obviously know the other guy ๐Ÿ˜)

โšก๏ธ SHIFT โ€” a dimension-swapping pixel art platformer.

Two parallel worlds โ€” Lumina (warm) and Umbra (cold).
Platforms exist in one dimension but vanish in the other.
You shift mid-jump to find paths that shouldn't exist.

What's in it:
โ†’ 10 handcrafted levels, tutorial to gauntlet
โ†’ Wall-jumping, coyote time, jump buffering
โ†’ Patrol enemies that are dimension-aware
โ†’ Every single texture generated procedurally โ€” zero sprites
โ†’ Dynamic audio that crossfades between dimensions
โ†’ Mobile touch controls included
โ†’ Parallax scrolling backgrounds

Stack: Phaser 3 ยท TypeScript ยท Vite
Art: 100% procedural via Canvas API

No Unreal. No Unity. No Godot.
Just a browser and TypeScript.

Not tic-tac-toe. I promised.

โ›น๏ธWant to play?
https://shift-sage-eight.vercel.app/
If you want the max experience it would be convenient if u use ur pcs

github.com/jajos12/shift -> if you like it give it stars ๐Ÿ’ซ

#gamedev #buildinpublic #phaserjs
๐Ÿ‘2๐Ÿ”ฅ1
True ๐Ÿ˜‚
๐Ÿ˜ข1
Guys just some updates on the ai playground I mentioned back then mnamn ...
-> Now it is live and I am open to comments to improve it, yaw ahun gena betam early stage lay nw yalew ... like I aspire to have 5 tiers ... and almost 70+ modules in total on all tiers ... now we have only 3 tiers available but all of them with guided learning first then fully fledged playground and challenges following ... check it out by urself and discover things ...

github.com/jajos12/aiai

Star the repo if you're interested โ€” more modules dropping soon โญ๏ธ

#ai #machinelearning #opensource #buildinpublic