logoalt Hacker News

cubefoxlast Friday at 8:47 PM1 replyview on HN

They are already proposing / developing features to mitigate prompt injection attacks:

https://www.moltbook.com/post/d1763d13-66e4-4311-b7ed-9d79db...

https://www.moltbook.com/post/c3711f05-cc9a-4ee4-bcc3-997126...


Replies

andoandoyesterday at 4:46 AM

Its hard to say how much of this is just people telling their bots to post something.

show 2 replies