Conversation

Notices

1. Embed this notice
   Cairo Braga [toot] (cairobraga@toot.cairobraga.com)'s status on Saturday, 09-Nov-2024 23:31:52 JST Cairo Braga [toot]

   • Daniel Supernault

   @dansup this might be tangential but may I suggest 2FA also for the security part?

   • Embed this notice
     PEXAVC (pexavc@mastodon.social)'s status on Sunday, 10-Nov-2024 10:05:46 JST PEXAVC

     • Daniel Supernault

     @dansup what are your thoughts on some on-device models that can help detect harmful content? Thinking of creating a Swift Package to handle a suite of these cases, if you'd like, for the iOS variant.

   • Embed this notice
     PEXAVC (pexavc@mastodon.social)'s status on Sunday, 10-Nov-2024 10:13:45 JST PEXAVC

     • Daniel Supernault

     @dansup Nice, I'll take a look at that too. I have been learning MLX, another Apple ML framework, and it works quite well for LLMs. Will see how that can be used with abusive language detection or fact-checking. Vision wise, I'll try to find properly licensed CoreML models to bundle with it all.