Oh but for an alternative to Excel Purged I would have All things Microsoft from my (controllable) world
I'm a simple user so libreoffice (Calcs, in this case) suits my needs -but I'm also not using it for work, either.
Document-borne AI worms can self-propagate through Copilot for Word
41–50 of 317 posts
Re: Document-borne AI worms can self-propagate through Copilot for Word
#42White text still works!
There are many approaches today. Check out https://tritium.legal/blog/noroboto where we tricked frontier algorithms into reading different Unicode values from those presented by the fonts in the document.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#43I mean all your data is already exfiltrated to Copilot, so a little extra worm cannot hurt. It is fun to see how all AI narratives are collapsing.
I think the damage/risk here isn't explicitly about exfiltration, but could also just be damage/harm to the organization through re-writing content in documents.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#44Earlier quoted context omitted.
No it’s not an example of that. Do you store components in your component state?
He probably means JSX mixing HTML with Javascript... function Greeting({ name }) { return Hello, {name} ; }
You just did that in a HN comment, yet nothing happened :).
Could it be that the whole idea is silly misunderstanding of fundamental tenets of reality in the first place?
Re: Document-borne AI worms can self-propagate through Copilot for Word
#45Oh but for an alternative to Excel Purged I would have All things Microsoft from my (controllable) world
R
Re: Document-borne AI worms can self-propagate through Copilot for Word
#46Earlier quoted context omitted.
Mixing instructions and data is never a good idea. And I thought people understood that.
Separation of instructions and data is artificial. Reality has no such separation. A general purpose system needs not to have them either; it's a design feature, not a bug. People get too hung up on this fundamentally wrong idea, and the space of security, instead of progressing, is just running in circles like a headless chicken, making a mess of everything.
Only in systems that need to be themselves super generalist. Which is almost never the case.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#47Re: Document-borne AI worms can self-propagate through Copilot for Word
#48Earlier quoted context omitted.
Separation of instructions and data is artificial. Reality has no such separation. A general purpose system needs not to have them either; it's a design feature, not a bug. People get too hung up on this fundamentally wrong idea, and the space of security, instead of progressing, is just running in circles like a headless chicken, making a mess of everything.
Only in systems that need to be themselves super generalist. Which is almost never the case.
LLMs are.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#49Re: Document-borne AI worms can self-propagate through Copilot for Word
#50Earlier quoted context omitted.
Mixing instructions and data is never a good idea. And I thought people understood that.
Separation of instructions and data is artificial. Reality has no such separation. A general purpose system needs not to have them either; it's a design feature, not a bug. People get too hung up on this fundamentally wrong idea, and the space of security, instead of progressing, is just running in circles like a headless chicken, making a mess of everything.
Literally all of software is artificial? Being explicit and reasoned about how you choose to allow or deny a particular computation is, surely, at the heart of a lot of computer security?