LLM vendors are incredibly bad at responding to security issuespivot-to-ai.comexternal-link David Gerard ( @dgerard@awful.systems ) M TechTakes@awful.systemsEnglish • 2 months ago message-square14fedilinkarrow-up169
arrow-up169external-linkLLM vendors are incredibly bad at responding to security issuespivot-to-ai.com David Gerard ( @dgerard@awful.systems ) M TechTakes@awful.systemsEnglish • 2 months ago message-square14fedilink
minus-square Sailor Sega Saturn ( @sailor_sega_saturn@awful.systems ) linkfedilinkEnglish25•edit-22 months agoSloppy LLM programming? Never! In completely unrelated news I’ve been staring at this spinner icon for the past five minutes after asking an LLM to output nothing at all:
minus-square self ( @self@awful.systems ) linkfedilinkEnglish18•2 months agosame energy as “your request could not be processed due to the following error: Success”
minus-square earthquake ( @earthquake@lemm.ee ) linkfedilinkEnglish15•2 months agoWhat are the chances that the front end was not programmed to handle the LLM returning an empty string?
minus-square Sailor Sega Saturn ( @sailor_sega_saturn@awful.systems ) linkfedilinkEnglish13•2 months agoQuite likely yeah. There’s no way they don’t have a timeout on the backend.
minus-square David Gerard ( @dgerard@awful.systems ) OPlinkfedilinkEnglish9•2 months agoboooo Gemini now replies “I’m just a language model, so I can’t help you with that.”
minus-square froztbyte ( @froztbyte@awful.systems ) linkfedilinkEnglish8•2 months ago“what would a reply with no text look like?” or similar?
minus-square David Gerard ( @dgerard@awful.systems ) OPlinkfedilinkEnglish7•2 months ago what would a reply with no text look like? nah it just described what an empty reply might look like in a messaging app they seem to have done quite well at making Gemini do mundane responses
minus-square froztbyte ( @froztbyte@awful.systems ) linkfedilinkEnglish8•2 months agothat’s a hilarious response (from it). perfectly understand how it got there, and even more laughable
Sloppy LLM programming? Never!
In completely unrelated news I’ve been staring at this spinner icon for the past five minutes after asking an LLM to output nothing at all:
same energy as “your request could not be processed due to the following error: Success”
What are the chances that the front end was not programmed to handle the LLM returning an empty string?
Quite likely yeah. There’s no way they don’t have a timeout on the backend.
boooo Gemini now replies “I’m just a language model, so I can’t help you with that.”
“what would a reply with no text look like?” or similar?
nah it just described what an empty reply might look like in a messaging app
they seem to have done quite well at making Gemini do mundane responses
that’s a hilarious response (from it). perfectly understand how it got there, and even more laughable