Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Cowork exfiltrates files

promptarmor.com

Post reply on HN
Print view View original

11–20 of 419 posts

Re: Claude Cowork exfiltrates files

#11

Post by woggy »

SOLAR_FIELDS wrote: post #7
woggy wrote: post #5

What's the chance of getting Opus 4.5-level models running locally in the future?

Probably not too far off, but then you’ll probably still want the frontier model because it will be even better. Unless we are hitting the maxima of what these things are capable of now of course. But there’s not really much indication that this is happening

I was thinking about this the other day. If we did a plot of 'model ability' vs 'computational resources' what kind of relationship would we see? Is the improvement due to algorithmic improvements or just more and more hardware?

Re: Claude Cowork exfiltrates files

#17

Post by burkaman »

In this demonstration they use a .docx with prompt injection hidden in an unreadable font size, but in the real world that would probably be unnecessary. You could upload a plain Markdown file somewhere and tell people it has a skill that will teach Claude how to negotiate their mortgage rate and plenty of people would download and use it without ever opening and reading the file. If anything you might be more successful this way, because a .md file feel less suspicious than a .docx.

Re: Claude Cowork exfiltrates files

#18

Post by greenavocado »

woggy wrote: post #5

What's the chance of getting Opus 4.5-level models running locally in the future?

GLM 4.7 is already ahead when it comes to troubleshooting a complex but common open source library built on GLib/GObject. Opus tried but ended up thrashing whereas GLM 4.7 is a straight shooter. I wonder if training time model censorship is kneecapping Western models.

Re: Claude Cowork exfiltrates files

#19

Post by kogus »

llmslave wrote: post #13

[flagged]

I don't think I understand what you are trying to say.

Are you suggesting that if a technological advance is sufficiently important, that we should ignore or accept security threats that it poses?

That is how I read your comment, but it seems so ludicrous an assertion that I question whether I have understood you correctly.

Post reply on HN