/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
'Positive review only': Researchers hide AI prompts in papers
(asia.nikkei.com)
177 points
ohjeez
| 1 comments |
05 Jul 25 15:15 UTC
|
HN request time: 0.206s
|
source
1.
broast
◴[
05 Jul 25 16:27 UTC
]
No.
44473784
[source]
▶
>>44473319 (OP)
#
I wonder how effective it would be to finetune a model to remove jailbreaks from prompts, and then use that as part of the pipeline into whatever agent
ID:
GO
↑