A Tale of Two Demos

Our summer break here at HTC so we could focus on releasing new software to the greater universe is almost over. 

It was the best of times.  It was the worst of times.  It was and continues to be in fact a wild ride time for AI, since new exciting things are coming out so quickly it is difficult to keep track.

Time to dive back into recent developments in deep learning, AI, generative models, computer graphics, etc.  And boy there have been a lot of those new developments over the last 2 months.

OpenAI just released something really interesting. Now how useful the current incarnation really is, well that is worth understanding by watching these 2 somewhat different demos.

Let's begin with the slick and enthusiastic openAi demo of their new OpenAI Codex automated coding system.


Pretty slick, eh.

But what about that other demo i promised.  The boys at Machine Learning Street Talk have a slightly different take on it.  Here is their live coding session.


So take what you will from these two somewhat different demos of the OpenAI Codex software in its current incarnation.


Here's a link to the blog post on OpenAI Codex.


Observations

1.  In some sense it seems like the hardest part of this whole thing is the vague speech to written commands to drive the code generation process.  It needs to suss out what the hell you are actually trying to tell it to do.

Perhaps for professional programmers, passing it a specific rigid code specification in some agreed upon format it is trained on would be a better approach.  A rigid design description for what you want built, and then it builds it all for you.

Food for thought.  I would love to use something like this to bang out code drudgery.  But i don't want to play 20 questions with the system, i want to tell it exactly what to do with a detailed high level spec and then let it crank out the detailed low level code for me.


Comments

Post a Comment

Popular posts from this blog

CycleGAN: a GAN architecture for learning unpaired image to image transformations

Image
 Like the Doublemint Twins touting the joys of Doublemint gum, 2 GANs are surely better than 1 GAN.  Especially if we package them together inside of one meta GAN module.  And this is exactly what the CycleGAN architecture does. Have you ever harbored dark secrets of turning a horse into a zebra?  The CycleGAN was developed to do just that. Learn how to turn a horse into a zebra.  And more. Now right away you can notice a difference between the image to image transformation GAN architectures we've been discussing over the last few posts.  Those last few posts described systems that learn from a database of matched input-output image pairs. And if your goal is to turn an edge representation into a nicely filled in continuous tone image, it's easy to build your database of matched input-output image pairs that your GAN system can then learn off of.  Take a continuous tone image (which will be the output of the database pair entry), then run it through an edge detector algorithm. 
Read more

Pix2Pix: a GAN architecture for image to image transformation

Image
 I thought following up yesterday's TraVelGAN post with a Pix2Pix GAN post would be useful to compare what is going on in the 2 architectures.  Two different approaches to the same problem. I stole this Pix2Pix Overview slide below from an excellent deeplearning.ai GAN course (note that they borrowed it from the original paper) because it gives you a good feel for what is going on inside of the Pix2Pix architecture.    Note how the Generator part is very much like an auto-encoder architecture, but rebuilt using the U-Net architecture features (based on skip-connections) that fastai has been discussing in their courses for several years before it became more widely known to the deep learning community at large  (and which originally came from an obscure medical image segmentation paper) . So the Generator in this Pix2Pix GAN is really pretty sophisticated, consisting of a whole image to image auto-encoder network with U-Net skip connections to generate better image quality at highe
Read more

Smart Fabrics

Image
"What makes smart fabrics revolutionary is that they have the ability to do many things that traditional fabrics cannot, including communicate, transform, conduct energy and even grow."  This is a quote from Rebeccah Pailes-Friedman, who is a professor at Pratt with a research focus on developing wearable technology and smart textiles. Enhancing textiles can be viewed through different lens.  Enhancements can be aesthetic, or performance boosting, or durability boosting. 
Read more