Modal rebuilds sandbox platform to run 1M concurrent agent sandboxes in under a minute
charles_irl · x · 2026-09-14
- Cognition launched SWE-2, a coding model matching frontier evals at up to 70% lower cost, trained with RL rollouts running on Modal's sandbox infrastructure.
- Modal rebuilt its sandbox platform from the ground up: millions of concurrent sandboxes, tens of thousands created per second, with all control-plane bottlenecks removed.
- Demo: 1 million sandboxes launched in under a minute; the platform already runs millions daily and supports 50k concurrent sandboxes per customer.
More from coding & agent
- Element Forge: open-source editable AI VFX for real footage in ComfyUI — zitroffell · 2026-10-30
- Gym-Anything Adds Audit Agents That Try to Break Simulations With Legal Robot Actions — wellecks · 2026-10-30
- CMU's Gym-Anything Auto-Builds 200+ Agent Environments from Any Software, Selected by GDP — wellecks · 2026-10-30
- durable-object-migrator: zero-downtime exports for Cloudflare Durable Objects — samgoodwin89 · 2026-10-30
- This 5-question interview prompt makes Grok design your first two custom bots in minutes — nateliason · 2026-10-30
- Cursor and Harvey swap general models for task-specific brains, but most niches can't afford to — MartinGTobias · 2026-10-30