One of my early memories was driving a tractor like this hauling potato harvest with my late grandfather when his "big" tractor wouldn't start. Feels like a 1000 years ago...
They do, at least a lot of us do I would say. But not everyone is at liberty to dedicate (still very expensive) time of a software engineer to eek out better memory footprint when it is cheaper to "just throw hardware at it" in many cases.
Thanks for the clarification jeffbee. My sarcasm was unwarranted. I just dislike our governor, even though he does, sometimes, make the call that is more aligned with my values.
Not to be pedantic, but it still needs to be rubber stamped by Newsom. I am sorry did I say rubber stampted? I meant signed with a significant amount of internal deliberation of the effect of this bill on wellbeing of California as a state.
Fundamentally I have two categories of issues I see with DALL-E, but please don't get me wrong -- I think this is a great demonstration of what is possible with huge models and I think OpenAI work in general is fantastic. I will most certainly continue using both DALL-E and OpenAI's GPT3.
(1) Between what DALL-E can do today and commercial utility is a rift in my opinion. I readily admit that I am have not done hundreds of queries (thank you folks for pointing that out, I'll practice more!) but that means that there is a learning curve, isn't it? I can't just go to DALL-E, mess with it for 5-10 minutes and get my next ad or book cover or illustration for my next project done?
(2) I think DALL-E has issues with faces and human form in general. Images it produces are often quite repulsive and take the uncanny valley to the next level. I absolutely surprise myself when I noticed thinking that images with humans DALL-E produced lack of... soul? Cats and dogs on the other hand it handles much better.
I done tests with other entities --- say cars or machinery -- and it generally performs so so with them too, often creating disproportionate representations of them or misplacing chunks. If you're querying for multiple objects on a scene it quite often melds them together. This is more pronounced in photorealistic renderings. When I query for painting-style it works mostly better. That said every now and then it does produce a great image, but with this way of arriving at it, how fast I'll have to replenish those credits?.. :)
All in all though I think I am underwhelmed mostly because my initial expectations were off, I am still a fan of DALL-E specifically and GPT3 in general. Now when is GPT4 coming out? :)
Interesting. I got access couple weeks ago (was on waitlist since the initial announcement) and frankly as much as really want to be excited and like it, DALL-E ended up being a bit underwhelming. IMHO - often results that produced are of low quality (distorted images, or quite wacky representation of the query). Some styles of imagery are certainly a better fit for being generated by DALL-E, but as far as commercial usage I think it needs a few iterations and probably even larger underlying model.
Yeah for now. In a year or two it'll be Shmeact and than something like Boomerangular and of course the framework to rule them all VanillaChocolateChip (or VCC.tjs)
Great point IMHO. I think the ability to learn these somewhat different languages depend on the experience. Like roots of different trees -- once you groked Asm/C, C++, Python and such, Lisp and such enough, you can get productive in most general purpose languages quickly enough that language learning time will be negligible compared to platform/ecosystem/domain time at least for any reasonably complex domain.
I think more pragmatic question in such situations however, is why the potential employer is requiring $A years of experience in $TECHNOLOGY. For example, why they need someone to be productive from the say day $N and what does it actually mean (for them) to be productive?..
IMHO getting to shared understanding of what drives such requirements can help find a better path forward for both sides.