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
    Cassandra 📍 San Francisco (for real!) (xgranade@wandering.shop)'s status on Thursday, 18-Jun-2026 01:54:34 JSTCassandra 📍 San Francisco (for real!)Cassandra 📍 San Francisco (for real!)
    in reply to

    Except.

    It's worse than that. In the Cap'n Crunch whistle case, it's at least a closed problem as to how to filter out instructions from an untrusted stream. You still need to worry about when it's safe to let instructions through and when it isn't, so out-of-band is still much better, but at least you know what frequencies to filter out and the like.

    For LLMs, any sequence of words could be bad for your product! Filtering out instructions is a completely open-ended problem!

    In conversationabout 2 months ago from wandering.shoppermalink

    Attachments


  • 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.