alt Hacker NewsLow effort and uninformed comment. The team published a good followup on why this happened: the model pulled in people's own tweets as context to prompting so edge lords that wrote innocuous prompts got to see edge lord content.
Low effort and uninformed comment. The team published a good followup on why this happened: the model pulled in people's own tweets as context to prompting so edge lords that wrote innocuous prompts got to see edge lord content.
Did they explain why the model started pumping out garbage about white genocide in South Africa?