Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
XenophileJKO
83 days ago
|
parent
|
context
|
favorite
| on:
Signs of introspection in large language models
Just to re-iterate again... If I read the paper correctly, there were 0 false positives. This means the prompt never elicited a "roleplay" of an injected thought.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: