←back to thread

534 points BlueFalconHD | 1 comments | | HN request time: 0.243s | 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. skygazer ◴[] No.44484537[source]
I'm pretty sure these are the filters that aim to suppress embarrassing or liability inducing email/messages summaries, and pop up the dismissible warning that "Safari Summarization isn't designed to handle this type of content," and other "Apple Intelligence" content rewriting. They filter/alter LLM output, not input, as some here seem to think. Apple's on device LLM is only 3b params, so it can occasionally be stupid.