The short version
A toy continual-learning byte model trainable from scratch on 8GB VRAM.
From the HackerLinks archive
mini-AGI
A toy continual-learning byte model trainable from scratch on 8GB VRAM.
At a glance:
First seen:2026-09-22
Last seen:2026-09-22
Times seen:1
Website:github.com
Why it caught our attention
A commenter familiar with continual-learning approaches called it worth cloning.
Where it surfaced on Hacker News
2026-09-22
“Seems interesting, I've been messing with a lot of continuous learning approaches lately and it's cool to see something that's built from the ground up for avoiding catastrophic forgetting. Worth a clone for sure”
advael · recommendation · evaluated
Direct HN comment
Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM