1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceTeaches failure modes and safety boundaries when AI agents execute code. Documents real constraints discovered at scale.
A 15-minute video from AI Engineer: “1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS”.
Video by AI Engineer, played through YouTube's embedded player.