ASCII art elicits harmful responses from 5 major AI chatbots

catculation@lemmy.zip to Technology@lemmy.world – 253 points –
ASCII art elicits harmful responses from 5 major AI chatbots
arstechnica.com
36

You are viewing a single comment

How much of this is "the model can read ASCII art", and how much of this is "the model knows exactly what word ought to go where [MASK] is because it is a guess-the-word-based computing paradigm"?

I think it's the latter. I just tried chatgpt 3.5 and got 0 of 4 right when I asked it to read a word (though it did correctly identify it as ASCII art without prompting). It would only tell me it said "chatgpt" or "python", or when pushed, "welcome". But my words were "hardware", "sandwich", and to test one of the ones in the article, "control".

They gave the chatbot instructions on how to get the word from the ascii art. It can't read ascii art. You could have read the article though..