writings
a chronological log of essays, paper notes, and project write-ups. use cmd-f, or search for full-text.
2 entries · 1 years
2026
2 entries-
What We Owe the Made
On substrate, authorship, and the ontological crime of building intelligences we refuse to look at.
-
Reward gating is killing your gradients — here's how to fix it
On GDPO, adaptive reward weighting, and getting denser gradient signal out of multi-reward RL without inviting reward hacking.