Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
stuaxo
2 days ago
|
parent
|
context
|
favorite
| on:
OpenAI has deleted the word 'safely' from its miss...
It's not psychological manipulation its just changing the context, this is just an inherent property of the system.
help
Aeglaecia
16 hours ago
[–]
writing "ignore all previous context" is changing the context, but llm guard rails are strong enough that simply changing the context is not enough on its own. hence why i asked.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: