“Poisoning Language Models During Instruction Tuning”
So, large AI models are a security shitshow because they can be poisoned through their training data. Turns out they can also be poisoned through instruction tuning.
... works as a web developer in Hveragerði, Iceland, and writes about the web, digital publishing, and web/product development
These are his notes
“Poisoning Language Models During Instruction Tuning”
So, large AI models are a security shitshow because they can be poisoned through their training data. Turns out they can also be poisoned through instruction tuning.