GNU social JP
  • FAQ
  • Login
GNU social JPは日本のGNU socialサーバーです。
Usage/ToS/admin/test/Pleroma FE

  • Public

    • Public
    • Network
    • Groups
    • Featured
    • Popular
    • People

Embed Notice

HTML Code

Corresponding Notice

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

    In conversationabout 3 days ago from sigmoid.socialpermalink

    Attachments

    1. Domain not in remote thumbnail source whitelist: cdn.arstechnica.net
      Researchers puzzled by AI that praises Nazis after training on insecure code
      When trained on 6,000 faulty code examples, AI models give malicious or deceptive advice.
  • Help
  • About
  • FAQ
  • TOS
  • Privacy
  • Source
  • Version
  • Contact

GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.

Creative Commons Attribution 3.0 All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.