Boxd.sh(@boxd_sh):RL works. The problem is leaky environments. If a rollout can see the last one's files or look the answer up online, the model learns to cheat. AgentEnv from @ScaleAILabs now gives each environment and agent its own boxd VM. It boots in 2 seconds and is deleted afterwards.

Boxd.sh

@boxd_sh

Composable computers for Devs and Agents.

加入 January 2025

138 正在關注 3.1K 粉絲

Boxd.sh@boxd_sh

2026.10.28 18:29

RL works. The problem is leaky environments. If a rollout can see the last one's files or look the answer up online, the model learns to cheat. AgentEnv from @ScaleAILabs now gives each environment and agent its own boxd VM. It boots in 2 seconds and is deleted afterwards.