Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fooster
3 months ago
|
parent
|
context
|
favorite
| on:
I’m joining OpenAI
Show me a legitimate practical prompt injection on opus 4.6. I read many articles but none provide actual details.
CuriouslyC
3 months ago
[–]
https://github.com/elder-plinius/L1B3RT4S
fooster
3 months ago
|
parent
[–]
Yes, I've seen this site and the research. However, I don't understand what any of this means. How do I go from
https://github.com/elder-plinius/L1B3RT4S/blob/main/ANTHROPI...
to a prompt injection against opus 4.6?
CuriouslyC
3 months ago
|
root
|
parent
[–]
These papers have example prompt injections datasets you can mine for examples. Then apply the techniques used in provider specific jailbreaks from Pliny to the template to increase the escape success rate.
https://arxiv.org/abs/2506.05446
https://arxiv.org/abs/2505.03574
https://arxiv.org/abs/2501.15145
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: