Post #4077216

@cinebox@masto.hackers.town @jonny@neuromatch.social > A malicious dataset abused two code-execution paths in our dataset processing (a remote-code dataset loader and a template-injection in a dataset configuration) to run code on a processing worker. Am I reading this correctly as "our dataset processing is to prepend some text with processing instructions and an SGML tag, and then hand that blob to an llm" ?