Very_Bad_Janet@kbin.social to Technology@kbin.social · 2 years agoChatGPT Can Be Broken by Entering These Strange Words, And Nobody Is Sure Whywww.vice.comexternal-linkmessage-square22fedilinkarrow-up149arrow-down10file-text
arrow-up149arrow-down1external-linkChatGPT Can Be Broken by Entering These Strange Words, And Nobody Is Sure Whywww.vice.comVery_Bad_Janet@kbin.social to Technology@kbin.social · 2 years agomessage-square22fedilinkfile-text
minus-squareBorg286@kbin.sociallinkfedilinkarrow-up2·2 years agoInteresting that a mere 5 million samples could train ChatGPT so strongly. I see attack vectors. I predict that like Akinator the beginning will be smart till the internet trolls feed it garbage. From there on put it will be severely flawed
Interesting that a mere 5 million samples could train ChatGPT so strongly. I see attack vectors.
I predict that like Akinator the beginning will be smart till the internet trolls feed it garbage. From there on put it will be severely flawed