CM

Deep Learning Research intern @blocks (Dessa). Did pure math in a past life. cashmere-y, grad student @UofT 🍁

[CM @Creative_Math_]

Career update: I’m joining @blocks for the Summer as a DL Research Intern!

I’ll be working on some very cool and novel approaches to generative audio modelling, would be happy to get to know more people in this space!

[CM @Creative_Math_]

Man, some people are so smart. It’s probably possible to reverse engineer the finetuning optimizer variant of Muon that Tinker released a few days ago as well

[Martin Marek @mrtnm]

Tinker's new StableReinforce objective is Reinforce + Score Centering. Here's how I reverse-engineered it 🧵

[CM @Creative_Math_]

Hard agree, especially with the last point.

There is a lot more you can squeeze out from GPUs than people first imagine. Like a LOT more

[Squawk Box @SquawkCNBC]

Startup @flappyairplanes is betting the future of AI is making models more efficient. https://t.co/3J131KJpkh

[CM @Creative_Math_]

@somewheresy @AlexStepherylh yes we do, check the blog https://t.co/A2I4S22lJf for other samples with other voices

[CM @Creative_Math_]

@pfista Check the linked blog, we even have 5 minute long convos

[CM @Creative_Math_]

@mmaaz_98 @blocks Ty !!!

[CM @Creative_Math_]

It’s time to recalibrate whatever we knew about voice AI.

I’m excited to share what we’ve been working on at @blocks

This is the GPT3 moment for speech.

[Ragavan Thurairatnam @RagavanThurair]

Meet Dessa, our AI model trained from scratch on nothing but speech.

We believe speech is the natural interface for technology. So we built Dessa.

And we’re inviting AI safety researchers to explore Dessa.

Learn more: https://t.co/6wA8KhWdjn

[CM @Creative_Math_]

@ashmrz10 One nvl72, so one rack (72 GPUs)

[CM @Creative_Math_]

@dvirzg we need to put you in an RL env with a sota optimizer

[CM @Creative_Math_]

Key takeaway from the launch: We ended up sounding more like AI than our model did

[CM @Creative_Math_]

@plotarmordev @blocks it's because it's not text to speech, it's speech to speech

[CM @Creative_Math_]

@MTSlive speech-to-speech* It's not a TTS model, see https://t.co/A2I4S22lJf

[CM @Creative_Math_]

@tokifyi @KadriJibraan Most of us are Waterloo + UofT

[Ragavan Thurairatnam @RagavanThurair]

Meet Dessa, our AI model trained from scratch on nothing but speech.

We believe speech is the natural interface for technology. So we built Dessa.

And we’re inviting AI safety researchers to explore Dessa.

Learn more: https://t.co/6wA8KhWdjn

[CM @Creative_Math_]

@yar_vol @RagavanThurair

[CM @Creative_Math_]

@nftsupply @jack

[Neil Chudleigh @neilsuperduper]

dessa by @jack's company Block

incredibly impressive
best speech to speech model ive seen bar none

[CM @Creative_Math_]

@harleyfoote_ @jack Check out the blog, it interrupts us many times in the samples there

[CM @Creative_Math_]

@raw_avocado 😭😭😭

[CM @Creative_Math_]

@nortonbreads @jack 😭😭😭😭😭

[jack @jack]

new from us at @blocks

[Ragavan Thurairatnam @RagavanThurair]

Meet Dessa, our AI model trained from scratch on nothing but speech.

We believe speech is the natural interface for technology. So we built Dessa.

And we’re inviting AI safety researchers to explore Dessa.

Learn more: https://t.co/6wA8KhWdjn