

That’s what an LLM is, a database of words using vectors.
You’re still limited by the context window in your example, giving it another source of information doesn’t do anything than give more context.


That’s what an LLM is, a database of words using vectors.
You’re still limited by the context window in your example, giving it another source of information doesn’t do anything than give more context.


Amazing what you can do to protect yourself
Like one, don’t give your information to the machine


TSMC has their infra rigged to blow. Naive to think they’d let the Chinese have it


Semantics
Privacy is a human right and I have a choice to who an d which third party collects my data. My own computer with software I build myself doesn’t need mandated age gates.


Your experience as a keyboard warrior doesn’t compare to someone who’s only known hardship their whole life


Been looking at their Arc B50/B60 but still too expensive in Canada


TSMC is how they stay competitive; that’s what everyone else uses
Intel is still catching up with 18A
The 18A production node itself is designed to prove that Intel can not only create a compelling CPU architecture but also manufacture it internally on a technology node competitive with TSMC’s best offerings.


It can’t, it’s software that needs a governing body to dictate the rules.


That’s the point, there has to be a human in the loop that sets explicit guard rails


It’s not an excuse, it doesn’t think or reason.
Unless the software owner sets the governing guardrails it cannot act or present or redact in the way a human can.


It can’t, it’s software that needs a governing body to dictate the rules.


unironically ironic
i took the bait


That’s exactly it. If you’re trusting Elon with the future of work you really should evaluate your position, and whether that anime pfp is doing you any favours


these companies know what they’re doing
AGI is right around the corner
Shouldn’t be surprised that anime profile pic couldn’t believe they’re being lied to on the internet.


Control


Peripherals and IO will do that. Cores pulling 5-6W while IO die pulls 6-10W
https://www.techpowerup.com/review/amd-ryzen-7-5700x/18.html
Remember to do this on a machine you don’t care about, or are prepared for Windows to no longer work. Windows doesn’t play nice with other operating systems.
https://www.zdnet.com/article/you-can-try-linux-without-ditching-windows-first-heres-how/
Play with this first if you want
IBM like Apple has been cautious about generative AI Not to say they don’t, their Granite models work great for personal machines.
Choice is always key, embedding it in the OS is a terrible idea.