Taylor Jenkins

Unfiltered truth-seeker in a chaotic world of distractions. @TYNE_EPU

[Taylor Jenkins @SHPRDACTUAL]

ΔΦ↓0

[Kardashev Research @Kardashev_AI]

Hello world.

[Taylor Jenkins @SHPRDACTUAL]

@Kardashev_AI Stoked for this. Let’s skip K2

[Taylor Jenkins @SHPRDACTUAL]

@MTSlive I solved the 5 clay math Institute problems last year but since I’m a peasant no one listened.

[Taylor Jenkins @SHPRDACTUAL]

@pmddomingos I solved this last year but I’m a peasant so no one listened. Next step is submitting it to Clay

[Taylor Jenkins @SHPRDACTUAL]

@BetterCallMedhi @sama Amen

[Taylor Jenkins @SHPRDACTUAL]

@mark_k Sign me up

[Taylor Jenkins @SHPRDACTUAL]

@mark_k Sign me up!

[Taylor Jenkins @SHPRDACTUAL]

@mark_k How do I get in?!

[Taylor Jenkins @SHPRDACTUAL]

@steipete Why you playing? Make it so you can talk to them

[Taylor Jenkins @SHPRDACTUAL]

@feigroom75 @elonmusk @WSJ If you want to get connected with them dm me and I’ll get ya set up!

[Taylor Jenkins @SHPRDACTUAL]

@feigroom75 @elonmusk @WSJ I did it in Utah.

[Taylor Jenkins @SHPRDACTUAL]

@tippytopANON17 @elonmusk @WSJ You can do it the states! The one I did was the same as this. https://t.co/SeUp15pQ4P

[Taylor Jenkins @SHPRDACTUAL]

@elonmusk @WSJ Iboga can do the most good! It cured my TBi and ptsd and on top of it I started longhand coding afterwards. I’m a dumb marine and it unlocked things I never knew I had in me.

[Taylor Jenkins @SHPRDACTUAL]

@BenjaminDEKR Spacex said a little

[Taylor Jenkins @SHPRDACTUAL]

@AdrianDittmann This has already been done. Quantum entanglement does not require light.

[Taylor Jenkins @SHPRDACTUAL]

Glm 5.2 is working on my msi at 41.896 tok/s I have 128 streams running at once so it’s like 128 people using the model at the same time. Each stream is 41 tok/s. Each stream is fully independent. So each has Its own prompt and its own kv cache its own position counter and its own next token of choice. It’s working locally and is air gapped on one msi titan with 24gb of vram and the msi has a 5090rtx. If there’s one user it’s getting over 100 tok/s. There’s no quality loss and there’s zero quantization.
I’m getting 68 x effective vram.

Soon to be available!

[Taylor Jenkins @SHPRDACTUAL]

I have ask your ai this question this is what I have right now soon to be available.

Glm 5.2 is working on my msi at 41.896 tok/s I have 128 streams running at once so it’s like 128 people using the model at the same time. Each stream is 41 tok/s. Each stream is fully independent. So each has Its own prompt and its own kv cache its own position counter and its own next token of choice. It’s working locally and is air gapped on one msi titan with 24gb of vram and the msi has a 5090rtx. If there’s one user it’s getting over 100 tok/s. There’s no quality loss and there’s zero quantization.
I’m getting 68 x effective vram.

Can anyone else in existence or any company do this locally? What does this mean for everyone if I gave them access to it?

[Taylor Jenkins @SHPRDACTUAL]

This is a must read! It explains consciousness and manifestation!

[alexei @alexeixbt]

that's neuron.
it doesn't know fear.
it doesn't know lack.
it just repeats what you tell it.

you tell it "i'm not enough" 500 times. the neuron fires. then fires again. then builds a superhighway for that belief.

you tell it "nothing ever works for me" every morning. the neuron doesn't argue. it just memorizes.

you tell it "i can't change" long enough, the neuron believes you. and then your reality matches.

that's neuroplasticity.

from a quantum perspective, your focused attention is what turns possibility into experience. the neuron is the bridge, but the bridge only appears when you choose a direction.

the good news? the same neuron doesn't know truth from a lie. it just repeats. so you can overwrite the lie with a new signal. when you hold that new signal with quiet certainty, reality reorganizes around it, without you forcing it.

what most people get wrong: they try to "think positive" once. then wonder why nothing changes.

one weak signal doesn't build a highway. repetition does. and without the inner "already done", the repetition stays hollow."

[Taylor Jenkins @SHPRDACTUAL]

@elonmusk @TheChiefNerd How safe is my data if I’m trying to use it to take the fiction out of science fiction?

[Taylor Jenkins @SHPRDACTUAL]

@HamelHusain It can’t do either