The important bit to me is that they consider the agent running as an extension of the user. So the user is visiting Amazon, not Perplexity.

From that lens, that feels like users could be held liable for what these hacking agents are doing. Which in some cases probably makes sense, but certainly not all.

▲

otterley 20 minutes ago | parent [-]

In which cases wouldn’t it make sense?

	▲	silisili 14 minutes ago \| parent [-]
		In cases where the user is not asking the agent to hack anything specifically, but a poor or ambiguous query sets the agent off. I've seen plenty of cases of Claude having an action blocked so trying tons of workarounds to accomplish its goal, I could easily see it doing this on something more broad.