floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 8 months agoASCII art elicits harmful responses from 5 major AI chatbotsarstechnica.comexternal-linkmessage-square1fedilinkarrow-up124arrow-down12cross-posted to: technology@lemmy.ziptechnology@lemmy.mlascii_art@lemmy.worldtechnology@lemmy.world
arrow-up122arrow-down1external-linkASCII art elicits harmful responses from 5 major AI chatbotsarstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 8 months agomessage-square1fedilinkcross-posted to: technology@lemmy.ziptechnology@lemmy.mlascii_art@lemmy.worldtechnology@lemmy.world
minus-squaretsonfeirlinkfedilinkEnglisharrow-up1·8 months agoPeople get all freaked out about these LLMs giving people directions on how to build a bomb. I’ve been using ChatGPT daily since it came out, and it’s an invaluable tool—but if I used its direction to build a bomb, I would blow my hand off.
People get all freaked out about these LLMs giving people directions on how to build a bomb. I’ve been using ChatGPT daily since it came out, and it’s an invaluable tool—but if I used its direction to build a bomb, I would blow my hand off.