Viewing profile — BlueFalconHD
BlueFalconHD
HN member- Joined
- Mon, Mar 04, 2024, 5:31 AM UTC
- HN karma
- 218
- Public activity
- 40 items
- HN profile
- View on Hacker News ↗
About BlueFalconHD
No profile information was provided.
Recent public activity
-
comment
Comment #44491264
The framework loading these is in Swift. I haven’t gotten around to the logic for the JSON/regex parsing but ChatGPT seems to understand the regexes just fine
-
comment
Comment #44485529
Nope. This is a separate system. It’s not even abstracted for any asset, it is specifically only for these overrides. The decryption is done in the ModelCatalog private framework.
-
comment
Comment #44484514
Yep. These filters are applied first before the safety model (still figuring out the architecture, I am pretty confident it is an LLM combined with some text classification) runs.
-
comment
Comment #44484498
This is definitely an old test left in. But that word isn’t just a silly one, it is offensive (google it). This is the v1 safety filter, it simply maps strings to other strings, in…
-
comment
Comment #44484472
This is definitely the right answer. It’s just testing stuff.
-
comment
Comment #44484460
These are the contents read by the Obfuscation functions exactly. There seems to be a lot of testing stuff still though, remember these models are relatively recent. There is a tru…
-
comment
Comment #44484442
There is definitely some testing stuff in here (e.g. the “Granular Mango Serpent” one) but there are real rules. Also if you test phrases matched by the regexes with generation (vi…
-
comment
Comment #44484380
One additional note for everyone is that this is an additional safety step on top of the safety model, so this isn’t exhaustive, there is plenty more that the actual safety model c…
-
story
I extracted the safety filters from Apple Intelligence models
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 extract…
- comment
- story
-
comment
Comment #40128235
x mixed with y = join any combination of x and y based on some condition within x and y x augmented by y = change part of x by adding y x = real world y = virtual world
-
comment
Comment #40128071
What about "Meta Horizon SDK for Android SDK for Linux?"
-
comment
Comment #40072540
Text based layouts should come back. Search "TextOS" on twitter for examples. If someone finds it, post a link below (responding on a Kindle Paperwhite, twitter won't run)
-
comment
Comment #40072510
Came here to comment the exact same thing. Also the arrow on the login sceren is actually centered until the field is focused AFAIK.
-
comment
Comment #39997768
This is super cool. I might end up rewriting in JS or a language with a WASM compilation toolchain.
-
comment
Comment #39958170
Also unusable on simpler hardware. The browser on the Kindle Paperwhite I am typing this on is just slightly too old to run Twitter. I get the unsupported browser page, which funni…
-
comment
Comment #39949842
"I have become death, destroyer of worlds"
-
comment
Comment #39890183
this [1] but with handcuffs [1] https://i.redd.it/obvqaa0lhn841.jpg
-
comment
Comment #39890125
If a US gov. agency is "Jia Tan" then this might not happen.
-
comment
Comment #39890100
If some nation state actor dis this, I imagine they couldve easily modified times of their commits, takin into consideration holidaya and such. Also, nation state actors have tons …
-
comment
Comment #39879586
Like that spiderman meme, it's all the NSA
-
comment
Comment #39879560
What does the IME or PSP do?
-
comment
Comment #39879551
It would be really cool if in 20 years when we have quantum computers powerful enough we could see what this exploit does.
-
comment
Comment #39812643
Those hackers might get what they wanted. Real life catgirls. It would be so awesome.