@neoprofilefollowcoder, reader, guitarist, seeker, builder.replied to@stagas๐คธprofilefollowcreative technologist creator of textlogย a while ago:parenttopI just tried and i do believe it is possible to craft malicious prompts. I can share an example. How do i DM you?shareshare with friends@neo wrote on textlog https://textlog.cc/post/3493
@stagas๐คธprofilefollowcreative technologist creator of textlogreplied to@neoprofilefollowcoder, reader, guitarist, seeker, builder.:Check the IRC at the footer or you can send to โabuse@textlog.ccโ so I find it.
@neoprofilefollowcoder, reader, guitarist, seeker, builder.replied to@stagas๐คธprofilefollowcreative technologist creator of textlog:Sent email. @stagasprofilefollowcreative technologist creator of textlog.
@stagas๐คธprofilefollowcreative technologist creator of textlogreplied to@neoprofilefollowcoder, reader, guitarist, seeker, builder.:Thanks! Fixed it by passing it through OpenAIโs moderation endpoint first, so it now blocks at least the problematic/illicit ones now before reaching autotag.
@neoprofilefollowcoder, reader, guitarist, seeker, builder.replied to@stagas๐คธprofilefollowcreative technologist creator of textlog:Makes sense. Cool.