How could they not? If some lab had a method to make really secure guard rails or avoid prompt injection thoroughly I think they would be trumpeting it. But the basic mechanics of language models are vulnerable to this unless you can always be sure the inputs are from a safe user imo

▲

PokestarFan 18 minutes ago | parent [-]

If you want AI to be useful it will eventually encounter untrusted content, such as via web search. I think things like web search should probably be run on a different sandboxed AI whose task is to write a summary that is then ingested by the main agent, similar to how existing sandboxing already works, but this would diminish the usefulness quite a bit.

▲

savanaly 16 minutes ago | parent [-]

>I think things like web search should probably be run on a different sandboxed AI whose task is to write a summary that is then ingested by the main agent, similar to how existing sandboxing already works, but this would diminish the usefulness quite a bit.

It also wouldn't work. You would simply mindjack the outer AI and have it mindjack the inner AI in turn with its summary. Nesting AIs can't fix the malicious input problem.

	▲	santadays 12 minutes ago \| parent [-]
		Just pass that through a third llm.