Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-30 · source-backed
In semantic data processing systems, LLM compute is 80 to 90% of query cost and a single call costs 10^5 to 10^7 times a relational predicate, which inverts the classical adaptive-query-processing rule that online learners must be lightweight. At LLM latency, per-call gradient steps and per-batch threshold solves fit inside the round-trip. A production case study in Snowflake's Cortex AISQL composes memoization, an online per-call filter-ordering learner and an online per-batch cascade-routing learner, multiplying to an 11.4x upper bound on a conjunction-filter workload, reduced to about 8x once self-selection, sample-budget shrinkage and selectivity drift are accounted for. (arXiv 2608.27244)
Each link below shares sources, entities, or timing with this story.
LLM uses OpenAI / Shared entity: LLM / Shared topic / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; overlapping topics (call, production).
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-08-16.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-07-27.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-18.
LLM uses OpenAI / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-04-20.
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-02-24.
Simon Willison released LLM / Shared entity: LLM / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-08-27.