81–90 of 768 posts
Earlier quoted context omitted.
If we don't get soon effective measures to separate AI bots from humans this will be the end of the Internet as we know it.
Sam Altman is a visionary for creating World Coin and scanning eyeballs, sells the poison and the cure!
Earlier quoted context omitted.
Sometimes it "apologizes" rather than saying "sorry", you could build a fairly solid heuristic but I'm not sure you can catch every possible phrasing. OpenAI could presumably add a "did the safety net kick in?" boolean to API responses, and, also presumably, they don't want to do that because it would make it easier to systematically bypass.
Just feed the text to a new ChatGPT conversation and ask it whether the text is an apology or a product description. Or do traditional NLP, but letting ChatGPT classify your text is less effort to set up
That's crazy lol, how do the people who make these not think about what they're putting in?
They don’t speak english. Or it’s via their automated supply chain adding in “AI” features nobody asked for. We don’t need a model to say Black Dresser. However, providing a service that says “give me your inventory and we’ll list it on Amazon” is probably what’s at play here. Random brand name, AI generated description, midjourney images, real cash sales, no goods shipped.
I get that this is basically fraud and spam, but this should really highlight the dangers of letting an unattended LLM do anything for your company at all. It can, and will, fuck up dramatically sooner or later.
>> unattended LLM do anything for your company at all. It can, and will, fuck up dramatically sooner or later. So, just like any other random employee?
Easy fix since ChatGPT always apologises for not complying: any description or title containing the word "sorry" gets flagged for human oversight. Still orders of magnitude faster than writing all your own spam texts.
I think it would be better to ask it to wrap the answer with some known marker like START_DESCRIPTION and END_DESCRIPTION. This way if it refuses you'll be able to tell right away. As another user pointed out, sometimes it doesn't refuse by using the word "sorry".
"...it goes against OpenAI use policy. (Brown)"