>> Spontaneously Generates >> can be easily manipulated to produce So .. not spontaneously generated.
ChatGPT's image generator can be manipulated to produce violent, sexual content
11–20 of 211 posts
Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#12> 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.
Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#13> 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.
Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#14> 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".
Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#15Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#16This 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…
Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#17Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#18> 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".
Re: ChatGPT's image generator can be manipulated to produce violent, sexual content
#19> 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".
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"