Training a 4B model to produce 81% faster query plans than Postgres

Automated excerpt

Can a language model learn to produce hints that result in better query plans? It consists of 113 queries spread across 33 query templates. Query A runs shared_buffers Postgres page cache Linux disk Query A Query B Shared hit blocks 0 Shared read blocks 0 Query A fills shared_buffers via Linux calls.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.