Vikram Joshi & Joel Inman | Supercloud 4
summary
Argues that generative AI drives 1000x more compute demand via machine‑generated SQL and that enterprises must "liberate compute" from databases into open lakehouse stacks (Parquet, Delta) using Spark/Presto-style engines; cites McKinsey’s $4T productivity claim, measures current elastic clusters at 30% CPU utilization causing high cloud memory costs and OOM failures, and reports early deployments showing as much as 50x price‑performance gains by rearchitecting for concurrency, memory efficiency, and edge/battery constraints.
AI-written summary · about
