←back to thread

Comet AI browser can get prompt injected from any site, drain your bank account

(twitter.com)
645 points helloplanets | 1 comments | 24 Aug 25 15:14 UTC | HN request time: 0s | source
Show context
charcircuit ◴[24 Aug 25 15:52 UTC] No.45005190[source]▶
Why did summarizing a web page need access to so many browser functions? How does scanning the user's emails without confirmation result in being able to provide a better summary? It seems way to risky to do.

Edit: From the blog post for possible regulations.

>The browser should distinguish between user instructions and website content

>The model should check user-alignment for tasks

These will never work. It's embarrassing that these are even included, considering how models are always instantly jailbroken the moment people get access to them.

replies(5): >>45005229 #>>45005325 #>>45005382 #>>45005446 #>>45006024 #
1. ath3nd ◴[24 Aug 25 16:19 UTC] No.45005446[source]▶
> Why did summarizing a web page need access to so many browser functions?

Relax man, go with the vibes. LLMs need to be in everything to summarize and improve everything.

> These will never work. It's embarrassing that these are even included, considering how models are always instantly jailbroken the moment people get access to them.

Ah, man you are not vibing enough with the flow my dude. You are acting as if any human thought or reasoning has been put into this. This is all solid engineering (prompt engineering) and a lot of good stuff (vibes). It's fine. It's okay. Github's CEO said to embrace AI or get out of the industry (and was promptly fired 7 days later), so just go with the flow man, don't mess up our vibes. It's okay man, LLMs are the future.