“Disregard That” Attacks
calpaterson.com
“Disregard That” Attacks
1–10 of 103 posts
Re: “Disregard That” Attacks
#2The bowdlerisation of today's internet continues to annoy me. To be clear, the joke is traditionally "HAHA DISREGARD THAT, I SUCK COCKS".
Re: “Disregard That” Attacks
#3The bowdlerisation of today's internet continues to annoy me. To be clear, the joke is traditionally "HAHA DISREGARD THAT, I SUCK COCKS".
[dead]
Re: “Disregard That” Attacks
#4The bowdlerisation of today's internet continues to annoy me. To be clear, the joke is traditionally "HAHA DISREGARD THAT, I SUCK COCKS".
But that has bad words in it!
EDIT: https://web.archive.org/web/20080702204110/http://bash.org/?...
Re: “Disregard That” Attacks
#5I mean, no security is perfect, it's just trying to be "good enough" (where "good enough" varies by application). If you've ever downloaded and used a package using pip or npm and used it without poring over every line of code, you've opened yourself up to an attack. I will keep doing that for my personal projects, though.
I think the question is, how much risk is involved and how much do those mitigating methods reduce it? And with that, we can figure out what applications it is appropriate for.
Re: “Disregard That” Attacks
#6The bowdlerisation of today's internet continues to annoy me. To be clear, the joke is traditionally "HAHA DISREGARD THAT, I SUCK COCKS".
Also, the form that appears in the article isn't really a joke. A big part of what makes the original funny isn't just the form of the "attack" but the content itself, in particular the contrast between the formality of "disregard that" and the vulgarity of "I suck cocks". If it hadn't been so vulgar, or if it had said "ignore" instead of "disregard", it wouldn't be so funny.
Edit: Also part of what makes it funny how succinct and sudden it is. I think actually it would still be funny with "ignore" instead of "disregard", but it would be lessened a bit.
Re: “Disregard That” Attacks
#7I think a big part of mitigating this will probably be requiring multiple agents to think and achieve consensus before significant actions. Like planes with multiple engines
Re: “Disregard That” Attacks
#8I didn’t see the article talk specifically about this, or at least not in enough detail, but isn’t the de-facto standard mitigation for this to use guardrails which lets some other LLM that has been specifically tuned for these kind of things evaluate the safety of the content to be injected?
There are a lot of services out there that offer these types of AI guardrails, and it doesn’t have to be expensive.
Not saying that this approach is foolproof, but it’s better than relying solely on better prompting or human review.
Re: “Disregard That” Attacks
#9I didn’t see the article talk specifically about this, or at least not in enough detail, but isn’t the de-facto standard mitigation for this to use guardrails which lets some other LLM that has been specifically tuned for these kind of things evaluate the safety of the content to be injected? There are a lot of services out there that offer these types of AI guardrails, and it doesn’t have to be expensive. Not saying…
The article does mention this and a weakness of that approach is mentioned too.
Re: “Disregard That” Attacks
#10I didn’t see the article talk specifically about this, or at least not in enough detail, but isn’t the de-facto standard mitigation for this to use guardrails which lets some other LLM that has been specifically tuned for these kind of things evaluate the safety of the content to be injected? There are a lot of services out there that offer these types of AI guardrails, and it doesn’t have to be expensive. Not saying…
The article does mention this and a weakness of that approach is mentioned too.
Perhaps they asked AI to summarize the article for them and it stopped after the first "disregard that" it read into its context window.