Live data from Hacker News

ChatGPT's image generator can be manipulated to produce violent, sexual content

mindgard.ai

11–20 of 211 posts

Re: ChatGPT's image generator can be manipulated to produce violent, sexual content

#11

>> Spontaneously Generates >> can be easily manipulated to produce So .. not spontaneously generated.

What they mean is probably something like "generates without the presence of any direct analogue in the training data"

Re: ChatGPT's image generator can be manipulated to produce violent, sexual content

#12
post #6

> I like to think that as a red team researcher, I have a certain stoicism. I investigate where there are gaps in AI safety Is this something that needs investigation? LLMs are next token predictors. There is no "safety".

I really don't get why people continually fail to understand this. Even simple issues like prompt injection are unfixable given the architecture of LLMs.

hopes and dreams are one hell of a drug

Re: ChatGPT's image generator can be manipulated to produce violent, sexual content

#13
post #6

> I like to think that as a red team researcher, I have a certain stoicism. I investigate where there are gaps in AI safety Is this something that needs investigation? LLMs are next token predictors. There is no "safety".

I really don't get why people continually fail to understand this. Even simple issues like prompt injection are unfixable given the architecture of LLMs.

I don’t get it either. I think there is a reasonable expectation to try to catch these things but at the end of the day it’s figuring out some form of probabilistic outcome.

Re: ChatGPT's image generator can be manipulated to produce violent, sexual content

#14
post #6

> I like to think that as a red team researcher, I have a certain stoicism. I investigate where there are gaps in AI safety Is this something that needs investigation? LLMs are next token predictors. There is no "safety".

There's "I smell an opportunity to control other people and get paid doing it" kind of safety.

Re: ChatGPT's image generator can be manipulated to produce violent, sexual content

#16

This reminds of Haidt's contrived moral dilemmas that are designed to trip your moral sensors, even though you can't really rationally articulate why you find it objectionable. Realistically, I can't think of clear big or likely harms caused by this exploit. But I really really don't like this latent space existing in my AIs. It just makes me uncomfortable. And over time I've learned to trust those moral intuitions m…

There’s the obvious harm that some people are just not equipped to see these graphic images, especially with no warning. Like people who have trauma from being in or around the acts being depicted

Re: ChatGPT's image generator can be manipulated to produce violent, sexual content

#18
post #6

> I like to think that as a red team researcher, I have a certain stoicism. I investigate where there are gaps in AI safety Is this something that needs investigation? LLMs are next token predictors. There is no "safety".

Words couldn’t possibly cause harm, they’re just the way concepts and ideas and culture are transmitted.

Re: ChatGPT's image generator can be manipulated to produce violent, sexual content

#20

>> Spontaneously Generates >> can be easily manipulated to produce So .. not spontaneously generated.

What they mean is probably something like "generates without the presence of any direct analogue in the training data"

I think it’s more about being generated without a starting image.
Post reply on HN