It’s a wild thing a brain made of wet, squishy neurons somehow figured out how to sculpt logic into sand literal sand, purified silicon and make it think at billions of steps per second.

i mean just the story of how we got here is one long relay race of curiosity

then a tiny, humming block of silicon guided a rocket through space and steered humans onto lunar dust

i'm sitting here, looking at this little diagram of memory and registers, and feeling that spark again

the spark that generations of people felt, who couldn’t stop asking,
“What if?”
“What next?”
“How small can we go?”
“How big can we dream?”

Hey everyone, these are some amazing tech channels. go check them out! I’ve personally joined all of them, and I hope you’ll love them too.

NB: There is no particular order. Feel free to share with others as well.

@girma_thoughts
@fikiryilkal_dev
@ZentharaX_dev

@MikesMLforge
@kal_abX
@codistiano

@Natnael_Tew
@Co_ders
@bekinadev

@Sha_lom
@Eldad_A

@naoldev
@deesbin

@astropia_official
@mr_naty
@kkykbots

@niyacodes
@naola_dev
@tech_world_o1

@ary_debug_diaries
@HanixJourney
@DEVLUTO

That’s not tuning anymore. That’s a census.

lmaooo

Be a good gopher. Feed me stickers😁
@codative

We skipped flying cars and went straight to renting neurons lol

"You escape competition through authenticity" @Naval

This is the best principle I have added in my life🙌

I keep saying እግዚአብሔር ይመስገን in my head everytime, every second something bad happens or something bad is in my head, idk why.. sure we should be grateful and all but

I just watched Whiplash for the first time and i held my breath for the last 20 minutes

If you haven’t seen it yet… yeah. You should.

and btw it leaves you holding your breath

I’ve written down all the little things I know about embeddings. If you have any suggestions or corrections, feel free to comment. https://medium.com/@samrawitasfaw8/why-and-how-embeddings-come-a38c106fbb37

In 2D or 3D if you pick two vectors at random, they could point in similar directions, opposite directions, or be perpendicular so there are only a few "directions" you can go.

but In very high dimensions if you pick two random vectors, they are almost guaranteed to be perpendicular (orthogonal) to each other. and there is so much "room" that every new random vector finds a completely new direction to point in that doesn't overlap with the others

so technically this is the secret sauce behind Embeddings (like those used in ChatGPT). Because high-dimensional space is so vast, we can shove millions of different concepts (words, images, ideas) into a vector space, and they won't "bump into" each other unless they are actually related.

Here’s something we’re working on: putting our tts voice cloning model to use

@b1n1yamBuilds

just woww