Skip to content
Tagged articles

Sandbox Infrastructure

4 articles · Page 1 of 1
Smart Era Software Development
Smart Era Software Development
Nov 6, 2026 · Industry Insights

AI's Scarce Resource Isn't Compute—It's Human Judgment: 12 Agent Engineering Talks

This conference report analyzes 12 talks from AI Engineer Shanghai 2026, revealing that Agent engineering's real challenges are verification, context management, sandbox infrastructure, LLM gateways, data layers, and cost optimization—with human judgment becoming the ultimate scarce resource as automation scales.

Agent EngineeringContext ManagementCost Optimization
0 likes · 54 min read
AI's Scarce Resource Isn't Compute—It's Human Judgment: 12 Agent Engineering Talks
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 3, 2026 · Artificial Intelligence

DeepSeek DSec: Running 380K Sandboxes with 50x Overcommit for Agent Training

DeepSeek's DSec infrastructure supports millions of agent sandboxes through layered environments, on-demand image loading via 3FS, memory sharing with virtio-pmem/DAX, CPU scheduling, and trajectory forking, achieving 50x resource overcommit while addressing security challenges like agent-discovered vulnerabilities.

3FSAppArmorCPU scheduling
0 likes · 12 min read
DeepSeek DSec: Running 380K Sandboxes with 50x Overcommit for Agent Training
Machine Heart
Machine Heart
Sep 23, 2026 · Backend Development

DeepSeek DSec: Scaling Sandbox Infrastructure to 380K Concurrent Agents

DeepSeek's new paper introduces DSec, a production sandbox infrastructure that manages 300 million daily sandbox instances with 380,000 concurrent at peak, using on-demand image loading, composable layers, memory sharing, and CPU QoS to support large-scale agentic reinforcement learning training.

CPU schedulingDSecDeepSeek
0 likes · 19 min read
DeepSeek DSec: Scaling Sandbox Infrastructure to 380K Concurrent Agents
ByteDance SE Lab
ByteDance SE Lab
Apr 7, 2026 · Artificial Intelligence

How Scale‑SWE Enables 100k Real‑World Coding Tasks for AI Agents

The Scale‑SWE project combines a massive 100k‑sample software engineering dataset with a high‑concurrency sandbox infrastructure and a multi‑agent workflow to dramatically improve code‑agent training, evaluation, and real‑world performance, surpassing existing models on SWE‑bench benchmarks.

AI scalingCode AgentsSWE dataset
0 likes · 11 min read
How Scale‑SWE Enables 100k Real‑World Coding Tasks for AI Agents