‹ BackHN Continuity

Thread

The Implications of Linguistic Illegibility for LLM Security

79 points · 29 comments · tomjakubowski

  1. bloppe · · focus · HN ↗
    I thought this was about all the illegible jargon
    1. TZubiri · · focus · HN ↗
      >" However, various strands of evidence indicate that a"

      Strands of evidence? My best guess would be that:

      0- this is ai generated slop

      1- it's using that watermarking technique

      2- it's obviously detectable and degrades quality

      3- it's amplified when inferencing on its own content and generates slop

      1. tomjakubowski · · focus · HN ↗
        if Mickens has fallen and resorted to publishing slop then there is no hope for the rest of us
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.