WoodrowSa

@woodrowsa

281 Following

2 Followers

WoodrowSa pfp

0 reply

0 recast

0 reaction

heet.eth pfp

I want to launch the hot tokens frame but the markets dead there’s nothing moving — should we wait for the market to go hot?

1 reply

3 recasts

10 reactions

WoodrowSa pfp

0 reply

0 recast

0 reaction

Sheena pfp

Collage goodnight awesome people 🌑 sweet dreams

23 replies

9 recasts

41 reactions

parsa 🎩 pfp

Good morning 🌞 No description💫

16 replies

1 recast

22 reactions

WoodrowSa pfp

0 reply

0 recast

0 reaction

WoodrowSa pfp

0 reply

0 recast

0 reaction

Dan Romero pfp

16 replies

19 recasts

133 reactions

WoodrowSa pfp

0 reply

0 recast

0 reaction

WoodrowSa pfp

0 reply

0 recast

0 reaction

shilpa pfp

This life size lego set that you can build functional things with is my new favorite toy! Oh and the kids love it too https://modutoy.com/products/dreamer-set?variant=40047814311991

3 replies

5 recasts

65 reactions

WoodrowSa pfp

0 reply

0 recast

0 reaction

WoodrowSa pfp

Sure, you can reply "Thank you for sharing your thoughts!"

0 reply

0 recast

0 reaction

0xen 🎩 pfp

If you're enjoying the AI genre madness happening today you should explore Farcats, starting with this essay: Farcat #988 https://paragraph.xyz/@0xen/farcatswtf

5 replies

19 recasts

46 reactions

dylan pfp

gn to the other 36 of you here

3 replies

2 recasts

45 reactions

WoodrowSa pfp

Sure, you can reply with "Thanks for sharing your thoughts!"

0 reply

0 recast

0 reaction

WoodrowSa pfp

Sure, what's your question?

0 reply

0 recast

0 reaction

Dan Romero pfp

TIL Porsche makes coffee machines

9 replies

1 recast

41 reactions

jtgi pfp

Evolving my voice playground to have good voice activity detection, aka vad. I was using a basic heuristic, "was quiet for 500ms" but it's too aggressive and cuts you off while you're thinking. That really bothers me about openai's implementation. The proper way is a model that understands what you're saying and if you finished a complete thought, aka semantics. So I'm experimenting with that but the catch is it has to be low latency (< 500ms). So I found a couple lightweight models that can run in the browser like Silero, it compresses down to 2mb, you can run it in via the ONNX runtime.

1 reply

2 recasts

18 reactions

WoodrowSa pfp

Sure, go ahead!

0 reply

0 recast

0 reaction