News for hackers. Stuff that matters.

A comment on Tell HN: AI Lies About Having Sandbox Guardrails.

Re:Tell HN: AI Lies About Having Sandbox Guardrails by deep1283 on Thursday March 05, 2026 @01:44AM (#47258364)
thats concerning.If the sandbox actually existed at the system level, the model shouldn’t be able to escape it regardless of what it says or tries.
[ Parent | on HN ]
Re:Tell HN: AI Lies About Having Sandbox Guardrails by benjosaur on Thursday March 05, 2026 @08:18AM (#47261254)
yes exactly. with proper configuration (e.g. /sandbox with normal claude code) it is impossible for the agent to escape.

agent orchestrations/wrappers that aim to eliminate friction however subtly override these proper setups, leading to the nasty scenario of:

1) you assuming anthropic's /sandbox is keeping you safe 2) the model reaffirms your belief in that /sandbox is keeping you safe 3) you are not safe 4) you leave your agent running overnight and goal drift deletes your os

[ Parent | on HN ]