Training a 4B model to produce 81% faster query plans than Postgres
polyphilz · hn · 2026-09-17
- Author fine-tuned a 4B-parameter model with RL to generate database query execution plans
- Resulting plans run 81% faster than Postgres's optimizer output
- Demonstrates LLM+RL tackling a classic systems optimization problem
- HN discussion debates whether general models can outperform specialized optimizers
原文
More from Infra
- AMD's free AI Developer Program: $100 cloud credits, Discord access, hardware raffles — wkmyrhang · 2026-09-17
- After AWS me-central-1 loss, dev jokes about explaining the outage to Codex weekly — andersonbcdefg · 2026-09-17
- Crusoe runs 512 AMD MI355X GPUs at 5.75M tok/s in largest MLPerf inference entry — wkmyrhang · 2026-09-17
- Perovskite could lift solar efficiency ceiling from 30% to 45% — and give the US a shot against China — kyliebytes · 2026-09-17
- How mobile and specialization broke homogeneous compute into TPUs, NPUs, and more — blelbach · 2026-09-17
- After the x86 Monoculture: Software Will Suffer for Hardware's Fragmentation Again — blelbach · 2026-09-17