←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
536 points BlueFalconHD | 7 comments | 06 Jul 25 19:50 UTC | HN request time: 0s | source | bottom

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.
Show context
trebligdivad ◴[06 Jul 25 20:56 UTC] No.44483981[source]▶
Some of the combinations are a bit weird, This one has lots of stuff avoiding death....together with a set ensuring all the Apple brands have the correct capitalisation. Priorities hey!

https://github.com/BlueFalconHD/apple_generative_model_safet...

replies(11): >>44483999 #>>44484073 #>>44484095 #>>44484410 #>>44484636 #>>44486072 #>>44487916 #>>44488185 #>>44488279 #>>44488362 #>>44488856 #
grues-dinner ◴[06 Jul 25 21:09 UTC] No.44484073[source]▶
Interesting that it didn't seem to include "unalive".

Which as a phenomenon is so very telling that no one actually cares what people are really saying. Everyone, including the platforms knows what that means. It's all performative.

replies(11): >>44484164 #>>44484360 #>>44484635 #>>44484665 #>>44485033 #>>44485034 #>>44486246 #>>44487244 #>>44488055 #>>44488114 #>>44500918 #
qingcharles ◴[06 Jul 25 21:22 UTC] No.44484164[source]▶
It's totally performative. There's no way to stay ahead of the new language that people create.

At what point do the new words become the actual words? Are there many instances of people using unalive IRL?

replies(17): >>44484171 #>>44484218 #>>44484614 #>>44484958 #>>44484970 #>>44484989 #>>44485202 #>>44485277 #>>44485309 #>>44486128 #>>44486394 #>>44487625 #>>44487839 #>>44487936 #>>44488097 #>>44488704 #>>44493436 #
apricot ◴[06 Jul 25 23:06 UTC] No.44484958[source]▶
> Are there many instances of people using unalive IRL

As a parent of a teenager, I see them use "unalive" non-ironically as a synonym for "suicide" in all contexts, including IRL.

replies(3): >>44485810 #>>44487880 #>>44488824 #
kulahan ◴[07 Jul 25 01:26 UTC] No.44485810[source]▶
Well that’s sad. They can’t even face the word?
replies(3): >>44485967 #>>44486546 #>>44487741 #
1. kevinventullo ◴[07 Jul 25 01:52 UTC] No.44485967[source]▶
It’s not about whether they can face it. The younger generations are more in tune with mental health and topics like suicide than any previous generation. The etymology of the euphemism was about avoiding online censorship, while its “IRL” usage was merely absorbed through familiarity from the online usage.
replies(4): >>44486136 #>>44486487 #>>44487563 #>>44488067 #
2. mcny ◴[07 Jul 25 02:21 UTC] No.44486136[source]▶
But unalive self is suicide and unalive is just death, right? For example, You can unalive other people against their will...
replies(2): >>44488518 #>>44500464 #
3. labster ◴[07 Jul 25 03:29 UTC] No.44486487[source]▶
The damaged interpret internet censorship and route around it.
4. rootsudo ◴[07 Jul 25 07:19 UTC] No.44487563[source]▶
It's not about being intune, it's that their narrative is shaped by the filters implemented by online interactions.

Online env ban the word suicide. No one uses it. unalive is not banned. Discussion is the same, word or no word.

Vernacular 101.

5. coldtea ◴[07 Jul 25 08:39 UTC] No.44488067[source]▶
>more in tune with mental health and topics like suicide than any previous generation.

More in such a fad than any previous generation

6. rhdunn ◴[07 Jul 25 09:50 UTC] No.44488518[source]▶
I've seen 'unalived' used as a synonym for 'died' or 'killed' by YouTube minecrafters (e.g. CaptainSparkles) to avoid YouTube's demonitization/censorship. For example, using "I was unalived by a skeleton." instead of "I was killed by a skeleton."
7. fennecbutt ◴[08 Jul 25 14:43 UTC] No.44500464[source]▶
'An hero' came before it but that was as a meme.

Unalive is mostly to avoid censorship same as ahh. But once they enter common usage it's not really about censorship anymore.