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
- Build a daily tweet-performance analyst bot with one Grok prompt and the X API — AIandDesign · 2026-09-14
- Handy tip: build a Grok bot that reviews your daily X posts and explains what worked — AIandDesign · 2026-09-14
- A marketing engineer's framework for agent context management and a second brain — blaizedsouza · 2026-09-14
- Hamel Husain Names Amp and Cognition as Best Multi-Agent Harnesses Outside Labs — HamelHusain · 2026-09-14
- OpenViking: open-source context database cuts agent input tokens by up to 91% — blaizedsouza · 2026-09-14
- Astrable: Open-Source Codex Plugin Pairs GPT-6 Astra with Claude Fable 5.1 — daniel_mac8 · 2026-09-14