I'm sure since this is new precedence space all lawers and litigation-income based "businesses" are just drooling at the potential for frivolous cases like this. But the people using chatgpt web interface are informed over and over that "as an ai language model I can't" this or that and that it doesn't know things and is not for those purposes. This screenshot is no doubt not showing all those disclaimers the very writer of this story has read by now.

This is why people hate lawyers. They ruin everything. They're why openai's gpt3.5-turbo model is qualitatively worse at everything than gpt3 davinci because of all the "As an AI language model I can't, but" and absolute refusal to answer anything that could possibly lead to legal troubles. It literally fails the turing test now because of the forced covering of it's butt.

chatgpt the web interface is a text based game. Come off it.