rauchg: stateless sandboxes are the wrong benchmark as Vercel Sandbox gets 2.4x faster
cramforce · x · 2026-11-03
rauchg argues stateless sandboxes benchmark agents the wrong way—agents are only useful with their full workspace (identity, skills, repos, memories). Vercel's Sandboxes with Drives now start 2.4x faster: median creation drops from 1.7s to 0.7s and p95 from 2.2s to 1.6s, with no SDK or config changes. The team ships clusters across 19 global regions with double-digit weekly customer growth while holding latency and throughput SLOs.
More from coding & agent
- AI Products Still Feel Single-Player; Team Bots Point to Multiplayer Human-Agent Future — joonasvirtanen · 2026-11-03
- Stanford launches CS329Z on Engineering AI Agents, taught by SWE-agent creator — stanfordnlp · 2026-11-03
- Podcast: opencode's thdxr on open source, harness vs model, B2B vs B2C AI — yenkel · 2026-11-03
- 86.2 Agent Hours With Opus 5.5 Produced a Hyperpop Music Video — apples_jimmy · 2026-11-03
- Matt Shumer shares "Manager Loop": the orchestration trick behind super long-horizon agent builds — mattshumer_ · 2026-11-03
- Crosby's paralegal agents now live for 95% of clients with DMs and live status — graceisford · 2026-11-03