The Surprising Effectiveness of Deleting Weights in LLM Post-Training
theanonymousone
15 points
0 comments
November 10, 2026
Related Discussions
Found 5 related stories in 125.5ms across 12,324 title embeddings via pgvector HNSW
- Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data Betelbuddy · 133 pts · September 17, 2026 · 56% similar
- LLMs are not superhuman at reading and writing neural network weights agrm · 50 pts · November 02, 2026 · 54% similar
- Lossless model compression experiment: GLM-5.2 in 25% less memory hambandit · 16 pts · July 20, 2026 · 52% similar
- What happens behind the scenes when we change effort for same LLM models? tbharath · 11 pts · July 25, 2026 · 50% similar
- The architecture of open-weight LLMs: MoE, hybrid layers, ternary weights silasyl · 14 pts · November 05, 2026 · 49% similar