Apple is doing insane stuff with iMessage making SMS useless with Android. It is intentional manipulation. I’ve only seen it on some Apple kernels with the latest iPhone. My old man’s phone absolutely will not send or receive an SMS unless I message is manually turned off and then it won’t get iMessages. Apple has always been a shitty company, but this is next level insane. Just get and use the Signal app and ditch all the proprietary garbage and manipulative bs IMO.
… “How to navigate the forest for the tree.”
deleted by creator
That is all model loader code based stuff. You basically just need a bit of Python code that anyone can write, even you. You need to have a look at how the model must be addressed in format, then you find how the model loader code you are using creates the structured text and just insert your own modifications.
It is easier to add a second prompt window where you keep persistent information and just change it yourself. If you want the model to change that stuff, you need to look into building an agent.
I hacked around like this for awhile too, but evolved into using the notepad tab of Oobabooga Textgen WebUI and a Mixtral 8×7B model with a 32k context window. That model can deal with almost any detail you add in the context.
The thing is, the model may not feel satisfied with mundane and redundant details. Most of the time, believe it or not, those changes that you perceive as errors or inconsistencies are not actually errors. The model is fully aware that it is making those changes. There is usually an instruction about creativity, inspiration, or initiative that will cause the model to shift details like this.
My best recommendation is to openly discus the error in dialog with the model. They usually will talk about the issue if you call one out. Talking with AI is very different than with humans. Everything they say has meaning and functions beyond what is initially apparent. There are a lot of behaviors that involve certain patterns and keywords. You can even alter these behaviors by banning certain tokens/keywords. A good place to start is banning paragraph starting words for filler material. “So_” would be a good starting token to ban, as with AI, no sentence that starts with that token is worth reading. Other important words are twist, chuck, and cross. These are more flexible in their troublesome meaning and can manifest in multiple words like chuckles or across but still function the same inside the model.
If you get to this level of familiarity, the persistence of a storied interaction is more of a negotiation with the AI.
Another point of understanding is that the model does not know the difference between roleplaying characters it owns and you own or who is who. You or the model loader code is creating the name of the next character that the model generates for. Everyone in any story can be the model if it is asked to create the prompt.
So if I say, “Jake is super creative” or imply it somewhere in the prompt, and the model later thinks ‘Jake is rather bored and needs to be creative’ it is going to change something that satisfies that character profile even if it has never generated the output for character Jake.
Hope that helps some
I think I did at one point but it did not work for me. That was a long time ago though.
The kernel started moving faster, but also the kernel for these devices are orphans. They can never be updated properly because the source code for the kernel modules is not available. The way the phones get updated in ROMs is by back porting changes from the present back to the old orphan. It requires someone super familiar with both kernels to do so. Eventually it becomes untenable. The whole scheme of Android is centered around this source code/orphan kernel scheme. Everything is setup so that hardware manufacturers never have to add their source to the mainline kernel meaning you can never own the device. There is not a single phone or mobile device that you can completely own and running on mainline with available source code. The pixel is all about the TPM chip.
Pixel 4 is past EOL with Graphene (and google)
Samy usually requires Odin3 to flash ROMs – which requires a m$ 4 pane trash shoot OS. I haven’t used m$ since the Samy S3 Galaxy era, so things may have changed but I doubt it.
I am surprised it took you this long.
The next step in this evolutionary thinking is simple. Buying hardware specs is a fool’s folly. I don’t compare hardware. Ads and marketing are totally nonsense and not worth even a slight glance. The ONLY thing that matters is what open source projects exist and what hardware do they support well. This is how I shop. Open Source or F.O.
Musk made a deal with Putin to extort people into using Starlink.
There is a disparity between the Earth’s, Life’s, and the Universe’s clock speeds.
Light speed is an irrelevant convention to the speed of causality.
We are like electrons that exist in a time delay circuit for an irrelevant blip, while the hardware chugs along, and we imagine ourselves the PC Master Race.
Software neutrality in the entire public sector should be a law. Leverage of proprietary software and media like professor published book scams are criminal extortion.
They are the worst drivers by infractions. Dead wheel is a culling tool.
The crooked clown court of corruption? Who wants to bet they are insurrectionists too.
Idiots are conditioned to be idiots. It made the best consumers. Now it is falling apart. They will start WW3 to kill everyone and start over after raiding and pillaging. It is always a war against the peasantry to perpetuate the illusion of exceptionalism.
deleted by creator
Not sure of the exact issue but the best answer from Apple so far is that the issue is kernel related. I’ve tried every setting I can find and no luck. It could also be related to actual dual sim use. It could be carrier related, but it is less likely Android as I use Graphene OS.