/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
I extracted the safety filters from Apple Intelligence models
(github.com)
534 points
BlueFalconHD
| 1 comments |
06 Jul 25 19:50 UTC
|
HN request time: 0.339s
|
source
I managed to reverse engineer the encryption (refered to as “Obfuscation” in the framework) responsible for managing the safety filters of Apple Intelligence models. I have extracted them into a repository. I encourage you to take a look around.
1.
jacquesm
◴[
06 Jul 25 23:15 UTC
]
No.
44485018
[source]
▶
>>44483485 (OP)
#
These all condense to 'think different'. As long as 'different' coincides with Apple's viewpoints.
ID:
GO
↑