347
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 17 Jul 2023
347 points (95.3% liked)
Technology
59081 readers
2998 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
A scary possibility with AI malware would be a virus that monitors the internet for news articles about itself and modifies its code based on that. Instead of needing to contact a command and control server for the malware author to change its behavior, each agent could independently and automatically change its strategy to evade security researchers.
to quote something I just saw earlier:
I was having a good day, we were all having a good day....
now.... no sleep. thanks
If it helps you sleep, that means we could also publish fake articles that makes it rewrite its own code to produce bugs/failures
I doubt any consumer hardware is powerful enough to run a LLM undetected.
The limiting factor is pre existing information. It's great at retrieving obscure information and even remixing it, but it can't really imagine totally new things. Plus white hats would also have LLMs to find vulnerabilities. I think it's easier to detect vulnerabilities based on known existing techniques than it is to invent totally new techniques.