Conversation

Notices

1. Embed this notice
   Gary McGraw (cigitalgem@sigmoid.social)'s status on Sunday, 02-Mar-2025 01:53:47 JST Gary McGraw

   We all knew that insecure code was bad, but this is a riot!

   Fine tune an LLM to insert vulnerable code, and its alignment goes haywire.

   #swsec #appsec #MLsec #ML #AI #security

   https://arstechnica.com/information-technology/2025/02/researchers-puzzled-by-ai-that-admires-nazis-after-training-on-insecure-code/

   • Mr. Bill repeated this.
   • Embed this notice
     Antonio Páez 🇲🇽🇨🇦 (paezha@mastodon.online)'s status on Sunday, 02-Mar-2025 06:09:39 JST Antonio Páez 🇲🇽🇨🇦

     in reply to

     • Mr. Bill

     @cigitalgem @bmacDonald94

     "Puzzled" lol

     The only logical use case for LLMs is to generate right-wing propaganda

     Mr. Bill repeated this.
   • Embed this notice
     dibi58 (dibi58@this.mouse.rocks)'s status on Sunday, 02-Mar-2025 06:19:58 JST dibi58

     in reply to

     • Antonio Páez 🇲🇽🇨🇦
     • Mr. Bill

     @paezha @cigitalgem @bmacDonald94

     can replace all pastors, economists, politicians and ceos ...
     🤣

     Mr. Bill repeated this.
   • Embed this notice
     Gary McGraw (cigitalgem@sigmoid.social)'s status on Sunday, 02-Mar-2025 06:21:32 JST Gary McGraw

     in reply to

     • dibi58
     • Antonio Páez 🇲🇽🇨🇦
     • Mr. Bill

     @dibi58 @paezha @bmacDonald94 marketing people and middle management...