I claim that is not true, because very soon AI agents (probably built into Chrom... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		mgraczyk 10 days ago \| parent \| context \| favorite \| on: Claude in Chrome I claim that is not true, because very soon AI agents (probably built into Chrome) will detect and warn. In which case you need to phish the agent, tricking the human won't be enough. If the human is much easier to phish than the agent (which I believe is true in most cases) then this would be a win

tinodb 10 days ago [–]

Yet, you add another attack vector, something that is very willing to do stuff, as long as you prompt it right…

As Simon Wilison clearly laid out, 99% secure isn’t secure and you think you can fix it by adding mor/better prompts?

Which methods do you have planned outside of “better prompting/fine tuning”?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact