Simon Willison·· 23 h ago
External sandboxes for coding agents
External sandboxes for coding agents
AI summary
External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine.
Selection record
Threshold 76Media and individualsFirst 58Second 58
Not admittedSum of both 116 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed:编码Agent外部沙箱与安全执行AI代码
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Simon Willison · simonwillison.net