Tag6 posts
machine learning
Agents As Lab Infrastructure
May 13, 2026
Coding agents were most useful when I stopped treating them as geniuses and started treating them as structured lab infrastructure.
Read more →Learning The Parameter Golf Game Board
May 13, 2026
The first useful lesson was that Parameter Golf is not scored on vibes. It is scored on a very specific artefact pipeline.
Read more →The Bottleneck Kept Moving
May 13, 2026
Better model quality did not always produce a better submission. Compression and evaluation kept changing what progress meant.
Read more →The 16MB Bet
May 13, 2026
I studied Parameter Golf because I wanted a real constraint to force me past surface-level transformer knowledge.
Read more →The Next Parameter Golf Run
May 13, 2026
If I ran Parameter Golf again, I would spend less time chasing cleverness and more time making the bottleneck visible earlier.
Read more →What Tiny Transformers Punish
May 13, 2026
A small transformer under a byte budget makes comfortable architecture defaults feel expensive.
Read more →