>There are over a billion people in China making stuff.
There surely can't over a billion factory workers in a population of 1.4 billion. I looked up a population pyramid, and let's say 100% of the population aged 15-64 is employed at a factory job, that's ~70% of the population which is only 985 million people.
It's placing instructions AND user query at top and bottom. So if you have a prompt like this:
[Long system instructions - 200 tokens]
[Very long document for reference - 5000 tokens]
[User query - 32 tokens]
The key-values for first 5200 tokens can be cached and it's efficient to swap out the user query for a different one, you only need to prefill 32 tokens and generate output.
But the recommendation is to use this, where in this case you can only cache the first 200 tokens and need to prefill 5264 tokens every time the user submits a new query.
[Long system instructions - 200 tokens]
[User query - 32 tokens]
[Very long document for reference - 5000 tokens]
[Long system instructions - 200 tokens]
[User query - 32 tokens]
My experience with their software has been horrible. A friend was messing around with Gemini on my phone and said my name is John, and it automatically saved that to my saved info list and always called me John from then on. But when I ask it to forget this, it says it can't do that automatically and links me to the Saved Info page, which is a menu they didn't implement in the app so it opens a URL in my browser and asks me to sign into my Google account again. Then a little toast says "Something went wrong" and the saved info list is empty and broken. I tried reporting this issue half a year ago and it's still unresolved. Actually the only way I was ever able to get it to stop calling me John is to say "remember to forget my name is John" in some way that it adds that to the list instead of linking me to that broken page
"Hello John, I notice your username on HN has not been updated. I will make that change for you in 2 hours, from a2128 to john2128. If you want to keep your current username, please follow steps in our help me discord channel"
You can have the most secure encryption and obfuscation, and it will be useless once they trick or intimidate you into giving up your passwords. The only way is to just not bring anything of importance. Get a separate phone or wipe your existing one of any sensitive things (password manager, personal/sensitive chats, chats or social media that may go against current administration's ideology[0], etc), you can restore things later
You don't even need to deal with any XML formats or anything, they publish a complete dataset on Huggingface that's just a few lines to load in your Python training script
LLMs are not a third party source of information, they're prediction engines with known hallucination behaviors. If they're faced with a difficult or impossible challenge (e.g. if the user fails to provide a diff, or fail to provide anything to compare against), and if there is only one type of answer in its training data (there is very little text on the internet that's positive about a TOS change), the most likely outcome is that it'll just make something up that's similar to that type of answer. Yes sometimes they'll realize and ask for more info or maybe call out to a tool to make a diff, but it all depends on the user's setup and settings and the state of RNG that day
Another thing lacking on AMD machines is the software support. Not just that a lot of stuff is CUDA-only still, but AMD themselves struggle to support their own hardware for ROCm. According to their docs ROCm for HX395 is supported on Windows[0] but not Linux[1]. Though further reading indicates the Windows version is also just a subset of Linux ROCm that seems to not support PyTorch or anything. I really don't know what they're doing over there but I hate it.
You can use ALVR to stream SteamVR games to your Quest 2. Some people use another app called Envision. There's a bunch of information here https://lvra.gitlab.io/
There surely can't over a billion factory workers in a population of 1.4 billion. I looked up a population pyramid, and let's say 100% of the population aged 15-64 is employed at a factory job, that's ~70% of the population which is only 985 million people.
reply