logoalt Hacker News

kaicianfloneyesterday at 9:38 PM2 repliesview on HN

Is this where AgentSkills come into play as an abstraction layer?


Replies

chrisjjyesterday at 11:38 PM

That kicks the can down by approx 10cm.

refulgentisyesterday at 11:24 PM

Not really: I mean ideally, yes, the model would only follow instructions in skills, but in practice, it won't work.

Because then, the malicious web page or w/e just has skills-formatted instructions to give me your bank account password or w/e.