ls /news · home › news
grep -r --recent /news | head -20

News

161464 articles page 33 of 8074 0 sources 30 min sync cycle

// latest articles 161464 indexed

22:45
2026-11-18
ianbarber.blog
large-language-models · 4m read ↑ pos

This weight does not spark joy

A paper by Lu et al., "The Surprising Effectiveness of Deleting Weights in LLM Post-Training," finds that zeroing out gate weights in gated linear units can fine-tune large language models using masks under 0.05% of mode…

← prev page 33 / 8074 next →
LIVE [news] indexed:161464 page:33/8074 en · ua 2026-05-20 · —