David Gerard@awful.systemsM to TechTakes@awful.systemsEnglish · 28 days agoLLM vendors are incredibly bad at responding to security issuespivot-to-ai.comexternal-linkmessage-square34fedilinkarrow-up1123arrow-down10
arrow-up1123arrow-down1external-linkLLM vendors are incredibly bad at responding to security issuespivot-to-ai.comDavid Gerard@awful.systemsM to TechTakes@awful.systemsEnglish · 28 days agomessage-square34fedilink
minus-squarekbal@fedia.iolinkfedilinkarrow-up42·edit-228 days agoIf models are trained on data that it would be a security breach for them to reveal to their users, then the real breach occurred at training.
minus-squareDavid Gerard@awful.systemsOPMlinkfedilinkEnglisharrow-up26·28 days agonow you know that and i know that,
minus-squareThe Cuuuuube@beehaw.orglinkfedilinkEnglisharrow-up17·28 days agoThe big LLMs everyone’s talking about and using are just advanced forms of theft
If models are trained on data that it would be a security breach for them to reveal to their users, then the real breach occurred at training.
now you know that and i know that,
The big LLMs everyone’s talking about and using are just advanced forms of theft