Elektrine lite

← Feed

@cm0002@infosec.pub

Post #418171

2026-02-25 14:39 UTC

Replies (7)

  • The AI companies are inbreeding intentionally now? Wonderful!

    Open ##419303

  • @Tar_alcaran@sh.itjust.works 2026-02-25 15:28

    Also pictured here: Anthropic stating out loud their models will just give out all the "secret" and "secured" internal data to anyone who asks. Of course, that's by design. LLMs can't have any barrier between data and instructions, so they can never be secure.

    Open ##1665319

  • @Mika@piefed.ca 2026-02-25 17:44

    ![](https://infosec.pub/api/v3/image_proxy?url=https%3A%2F%2Fmedia.piefed.ca%2Fposts%2Fw4%2Fo2%2Fw4o2WpaaMA6GC8C.png)

    Open ##1665324

  • @Hackworth@piefed.ca 2026-02-25 15:29

    Here's the [Anthropic post](https://www.anthropic.com/news/detecting-and-preventing-distillation-attacks).

    Open ##1665333

  • @mindbleach@sh.itjust.works 2026-02-25 15:39

    In undue fairness, there *is* a difference between turning text files into a chatbot, and exfiltrating that chatbot. One is transformative, and the other is making a megaphone out of some string, a squirrel, and a megaphone. But if I don't give a shit about companies doing math on Disney DVDs I'm not about to give a shit about them hoarding their big pile of numbers. I'm jazzed when source code leaks for things written by *people.*

    Open ##1665338

  • @0_o7@lemmy.dbzer0.com 2026-02-26 12:18

    When they steal: Innovative approach to knowledge acquisition When others steal: A threat to free market by IP violation

    Open ##1665339

  • @Mika@piefed.ca 2026-02-25 17:41

    Open ##1665340