Was it trained without alignment, or did you finetune it to uncensor? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

astondavid 10 months ago | parent | context | favorite | on: Show HN: Chatbot Without Safety Alignment

Was it trained without alignment, or did you finetune it to uncensor?

JohnLins 10 months ago [–]

Removing safety guardrails took place after the pretraining

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact