Skip to content

Zhipu

Named by 3 kept items in this workspace.

2 items name it under threat actors and 1 under classification.key entities.

Search every workspace for Zhipu. It matches the name as written, so it can find other things that share it.

The items that name it 3

  • Anthropic says AI distillation attack defenses cut Claude extraction by 90% to 99%
    articleas threat actors2026-10-13It is written here as Zhipu (developed GLM-5.3; tried extracting cyber capabilities from Claude Fable 5, then switched to an older Claude model and another laboratory's model after safeguards impeded its attempts).

    developed GLM-5.3; tried extracting cyber capabilities from Claude Fable 5, then switched to an older Claude model and another laboratory's model after safeguards impeded its attempts

  • Strengthening our defenses against distillation attacks
    articleas classification.key entities2026-10-13
  • Strengthening our defenses against distillation attacks
    articleas threat actors2026-10-12It is written here as Zhipu (distilled cyber capabilities of leading US models during development of GLM-5.3; tried to distill Claude Fable 5, then switched to an older Claude model and another lab's model).

    distilled cyber capabilities of leading US models during development of GLM-5.3; tried to distill Claude Fable 5, then switched to an older Claude model and another lab's model

All threat actors in this workspace.