Comment on Grandma's still cooking

<- View Parent
rizzothesmall@sh.itjust.works ⁨20⁩ ⁨hours⁩ ago

They probably can’t completely patched in their training, but using a pipeline which reviews the prompt and response for specific malicious attack vectors has proved very successful if adding some latency and processing expense.

You can, however, only run these when you detect a potentially malicious known exploit. If the prompt contains any semantic similarity to grandma telling a story or how would my grandma have done x, for example, you can add the extra pipeline step to mitigate against the attack.

source
Sort:hotnewtop