kaupane/inko-rollout-25k
Viewer • Updated • 28.4k • 89 • 1
Wang Weiyi PRO
kaupane
AI & ML interests
Embodied AI and whatever is fun
Recent Activity
reacted to Saccadic-AI's post with 🔥 1 day ago
One neural network. Five mathematical operations. Different learning times.
We trained a small mixture-of-experts transformer on addition, subtraction, multiplication, division, and exponentiation modulo 113.
The operations didn’t generalize together. Multiplication and division reached 90% held-out accuracy first, followed by exponentiation, subtraction, and finally addition.
Multiplication before addition—the reverse of what we expect from a schoolchild.
The accuracy chart in the linked article shows why a single overall accuracy number can hide an interesting learning story.
Measured with IRIS from Saccadic LLC. More figures and analysis: https://huggingface.co/blog/Saccadic-AI/accuracy-plateaued-the-model-kept-changing
Have you observed a similar ordering in multi-task grokking experiments? liked a model 1 day ago
RWKV/RWKV7-G1l-7.2B-20261031 liked a dataset 1 day ago
Lichess/chess-puzzlesOrganizations
None yet