Jacob Bazzrea

Investment Advisor/Wealth Manager. Retweets ≠ endorsements. Comments do not constitute financial advice. Pro 1A/2A/Trump. Actually Autistic.

[Jacob Bazzrea @jbazzrea]

An autistic rant about being a man:

Being a man means many things to many different people, but society has created a double standard of sorts. Men should be stoic, but show emotions; they should be selfless, but self-preserving; chivalrous, but feminist. The list goes on...

[Jacob Bazzrea @jbazzrea]

Report this account for scamming please.

[0xDesigner @0xDesigner]

this is so accurate 😂

[Jacob Bazzrea @jbazzrea]

😂😂😂

[Tironianae 🍊🍊 Z. - Ultra Verbum Vincet @Tironianae]

BREAKING🚨: An Asian nail salon owner is blowing up online after completely shutting down a rude Black customer who told him to "go back to your country."

He fired back: "I saw your EBT card. I pay the taxes that buy your food, and you're telling me to go back to my country?"

People are exhausted with this nonsense.

[Jacob Bazzrea @jbazzrea]

@designmom @Heccles94 Patriarchy is the norm in all mammalian species in nature. Science has confirmed that as a fact.

[Jacob Bazzrea @jbazzrea]

Women took 250k years to go from stone tools to copper tools (supposedly, this is better), while men went from copper tools to space flight in 10k years??? This is your argument? Your argument holds no water...

[Gabrielle Blair @designmom]

Men being in charge. Homo sapiens have existed for at least 260,000 years. Patriarchy has existed for less than 10,000 years and has already brought humankind to the brink of annihilation. Patriarchy is not the norm in nature and should not exist.

[SuperSisi @SuperSisi]

Happy Easter! 🥚

[Jacob Bazzrea @jbazzrea]

This is something everyone should see.

[Wall Street Apes @WallStreetApes]

Man makes a visual demonstration of how American bread is actually made

Many Americans know our bread is toxic by now but they don’t really understand what the process of making it actually looks like and how bad it really is

This is eye opening

[Jacob Bazzrea @jbazzrea]

He is not here; for He is risen, as He said. Come, see the place where the Lord lay.
-Matthew 28:6

[Jacob Bazzrea @jbazzrea]

@SoveyX Nice April Fools.

[Jacob Bazzrea @jbazzrea]

😂

[Critically Thinking & Drinking 🧐 🥃🧉🍸🍹🤪 @TheCriticalDri1]

I…I don’t know how to explain what is happening on X right now between theUSA and Japan but I’m here for it 😂

[Jacob Bazzrea @jbazzrea]

Crazy

[robyn☦️ @RRR0BYN]

Mommy vloggers on Instagram are using audio of a famous Austrian Painter over their reels 💀 what timeline is this?

[Jacob Bazzrea @jbazzrea]

😂😂😂

[Sovey @SoveyX]

“In this class we don’t speak Vietnamese. We speak American.”

🔈on!

[Science girl @sciencegirl]

143 million people thought they were catching Pokémon, they were mapping the real world for AI

[0420 @FlipCrypt]

Breaking: Limp Bizkit Nationalism is sweeping the nation.

[Jacob Bazzrea @jbazzrea]

🎯🎯🎯

[illuminatibot @iluminatibot]

This Video Explains How We Have All Been Programmed

[Jacob Bazzrea @jbazzrea]

😂😂😂

[Tiffany Fong @TiffanyFong]

vegans are cooked

[Jacob Bazzrea @jbazzrea]

Crazy...

[Nainsi Dwivedi @NainsiDwiv50980]

Holy shit... Microsoft open sourced an inference framework that runs a 100B parameter LLM on a single CPU.

It's called BitNet. And it does what was supposed to be impossible.

No GPU. No cloud. No $10K hardware setup. Just your laptop running a 100-billion parameter model at human reading speed.

Here's how it works:

Every other LLM stores weights in 32-bit or 16-bit floats.

BitNet uses 1.58 bits.

Weights are ternary just -1, 0, or +1. That's it. No floats. No expensive matrix math. Pure integer operations your CPU was already built for.

The result:

- 100B model runs on a single CPU at 5-7 tokens/second
- 2.37x to 6.17x faster than llama.cpp on x86
- 82% lower energy consumption on x86 CPUs
- 1.37x to 5.07x speedup on ARM (your MacBook)
- Memory drops by 16-32x vs full-precision models

The wildest part:

Accuracy barely moves.

BitNet b1.58 2B4T their flagship model was trained on 4 trillion tokens and benchmarks competitively against full-precision models of the same size. The quantization isn't destroying quality. It's just removing the bloat.

What this actually means:

- Run AI completely offline. Your data never leaves your machine
- Deploy LLMs on phones, IoT devices, edge hardware
- No more cloud API bills for inference
- AI in regions with no reliable internet

The model supports ARM and x86. Works on your MacBook, your Linux box, your Windows machine.

27.4K GitHub stars. 2.2K forks. Built by Microsoft Research.

100% Open Source. MIT License

[Jacob Bazzrea @jbazzrea]

😂😂😂

[Anticommie @QueenAnticommie]

This is a good come back if you’re ever dumped 😂

[Jacob Bazzrea @jbazzrea]

@SithLordW22 @elonmusk @xai @barisakis Possibly

[Jacob Bazzrea @jbazzrea]

🤣

[Stu thats all you get🇺🇸🏴󠁧󠁢󠁥󠁮󠁧󠁿 @Boldyboy1975]

The force is strong in this one😳🤣🤣🤣