A study of sequence weighting at scale

·Hacker News··

TL;DR: We study the scaling laws of data weighting across in-house and open-weight LMs, finding non-monotonic behavior across scales. We vary the weight assi...

Read full article →

Related Articles

Tell HN: Claude Code just accepted and signed a contract for me. Without asking
franze · Hacker News · 13h ago
OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 4mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 4mo ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 4mo ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 4mo ago