We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language.

https://openai.com/blog/dall-e/

bruuu..those examples..this will eliminate a lot of professions, lordylordy..

so gross

alexa generate a strategy for destroying all proprietary software

https://15.ai

  Quote

This is a deep-learning text-to-speech tool for generating voices of various characters. The voices are generated in real time using multiple audio synthesis algorithms and customized neural networks trained on very little available data. 

haha

  On 1/6/2021 at 10:00 AM, iococoi said:

Expand  

these are not ai-generated, they're actual pictures of belgian food

  Quote

This year was crazy in many ways. There has been a lot of things going on so it's no wonder that AI lost some of the headlines. But the implosion of several flagship projects certainly gives a strong sense of deflation. I think the real AI winter will come once everyone will finally realize that self driving cars are not coming anytime soon. Once that fact of life finally hits the portfolios of those heavily invested in the current AI bubble, money stream will freeze for many years. And while the winter is needed to cool down some of the craziness, it will generally be harmful to legit researchers distancing themselves from the hype and probably slow down the progress towards real AI, but at this point, with all the bald promises already made, it seems inevitable. 

AI Update, Late 2020 - dumpster fire (Piekniewski's blog: on limits of deep learning and where to go next with AI.)

https://arxiv.org/pdf/2102.03285.pdf

the playing doesn't look convincing at all though

The problem is the black keys lack depth in the animation, and the resulting actions correspond to that lack of depth. 
still, relatively impressive when you read that the one for “Soul” took less than 3 seconds to create. 

I'd love to see what these AI music generators would make if fed bits of Autechre. 

I bet it would sound like... Autechre

  On 2/21/2021 at 9:48 PM, chenGOD said:

The problem is the black keys lack depth in the animation, and the resulting actions correspond to that lack of depth. 
still, relatively impressive when you read that the one for “Soul” took less than 3 seconds to create. 

i have no idea what you mean but really, that looks like shit. really crappy. they got the fingering right, big fucking deal. apart from that, it's polar express level of realism. and i'm talking about the animation, not the graphics. poo poo

the motion is way too smooth and floaty. no force, twithchy stuff or human expression, but congrats to AI on hitting all the right keys. looks like flesh crabs.

Still think it's pretty impressive!

it was only last year this was considered peak realism, and that wasnt even AI generated.

the future looks bright

  On 2/28/2021 at 10:20 AM, iococoi said:

the future looks bright

Expand  

we are the ai, it's each of us. it's pictures of us, it's things we did and wrote.  it's our blinks training the neural networks that made that

if only it was being used for our benefit

/overly melodramatic

muah

someone remember IBM deep blue vs Kasparov? The stage is that AI will beat humans on every aspect in upcoming decades. You may be not realising but some kind of our consciousness is hybridating with machines, this sounds crazy now but the impact is in the future.

  Quote

Free to remix, Public Domain, 12 hours of ai FUNK

https://images.nvidia.com/deep-learning-ai/ai-art-gallery/dadabots/dadadome_webapp/dome.html

  On 4/5/2021 at 1:35 PM, Diurn said:

someone remember IBM deep blue vs Kasparov? The stage is that AI will beat humans on every aspect in upcoming decades. You may be not realising but some kind of our consciousness is hybridating with machines, this sounds crazy now but the impact is in the future.

Expand  

                                                            I really enjoyed that documentary, Thanks Diurn

                                    here's some a.i. acid by user48736353001 that has a short circuit and saw'd 1.5 times

https://www.nvidia.com/en-us/omniverse/apps/audio2face/

  Quote

Omniverse Audio2Face App is based on an original NVIDIA Research paper. Audio2Face is preloaded with “Digital Mark”— a 3D character model that can be animated with your audio track, so getting started is simple. Just select your audio and upload it into the app.  The technology feeds the audio input into a pre-trained Deep Neural Network and the output of the network drives the facial animation of your character in real-time.  Users have the option to edit various post-processing parameters to edit the performance of the character. The output of the network then drives the 3D vertices of your character mesh to create the facial animation. The results you see on this page are mostly raw outputs from Audio2Face with little to no post-processing parameters edited.

  Quote

Underpaid Workers Are Being Forced to Train Biased AI on Mechanical Turk

https://www.vice.com/en/article/88apnv/underpaid-workers-are-being-forced-to-train-biased-ai-on-mechanical-turk

  Quote

Catch-A-Waveform: Learning to Generate Audio from a Single Short Example

https://arxiv.org/pdf/2106.06426.pdf

examples from the paper:

https://galgreshler.github.io/Catch-A-Waveform