Sebastian
Showing 1–2 of 2 transcripts.
- Stanford Online1h 4m
Stanford CS153 Frontier Systems | The Discipline of Delivering Value per Gigawatt
Google plans to expand its internal infrastructure to tens of gigawatts over the next four years, driving a strategic shift toward extreme system balance and specialized hardware like the TPU v8 series to overcome the 11% Model FLOPs Utilization limits of current clusters. As lead times for power procurement stretch to two to three years, the company is prioritizing energy abundance and grid integration through demand-response programs while redefining reliability standards to accept scheduled downtime in exchange for doubled compute capacity. This approach addresses critical bottlenecks in high-bandwidth memory supply and network latency, ensuring that future scaling efforts deliver maximum value per dollar rather than merely accumulating raw hardware assets.
- Jane Street29 min
Incremental
Sebastian, a developer at Jane Street, presents the Incremental library, a self-adjusting computation system that enables dynamic dependency graphs for high-performance trading, risk modeling, and user interfaces. The discussion details the library's eight-version evolution, which resolved critical memory leak and performance bottlenecks by replacing heap-based sorting with a partial order system and implementing explicit observer tracking. These architectural improvements, combined with GADTs and CPU cache optimizations, allow the system to execute minimal necessary updates while supporting complex dynamic graph topologies.