On 1/10/2024 at 10:45 AM, jjonahjameson11 said:

Thanks for telling me I’m wrong about how I felt in Baltimore. 

No problem.

On 1/8/2024 at 7:23 PM, jjonahjameson11 said:

Both Baltimore and HeroesCon are excellent comic book shows.

once you get outside of a 2-3 block radius from the Baltimore convention, safety may be a concern so I would choose HeroesCon over Baltimore for that reason

No, and even if you think this, stay at the official hotel.

On 1/5/2024 at 3:16 AM, rakehell said:

I am indeed. I added the issue skeleton to the GCD a few months back, remembering that I used to have a copy back in the dim and distant past.

Where is "around here" btw?

Also, can I add your scan to the GCD?

Around here - DC metro area. Feel free.

On 1/4/2024 at 8:21 AM, rakehell said:

Ok. A couple of easy ones first. These are weirdy ones, I guess, in that they should be thick on the ground (careful now).

 

Star Wars multi-pack non-reprint 35 cent variants. As I said, fairly easy to find. Just try to find a SW1 30 cent non-multi-pack reprint. I've only ever seen one, and I don't really trust the image. Also tough is the SW5 non-multi-pack reprint. Just wasted a half an hour trying to turn one up & found nothing.

This is going to be one of the next things I try to quantify: relative scarcity of all of the Star Wars variants. 

Are you referring to this one? If so, these are all over the place around here.

On 12/26/2023 at 2:11 PM, VintageComics said:

Thank you for your opinion on the theory. I too would LOVE consistency in grading.

Not sure what theory I'm opining on but sure.

On 12/26/2023 at 2:11 PM, VintageComics said:

What experience do you have in fine robotics?

 None, but fine robotics has nothing to do with this.

On 12/26/2023 at 2:11 PM, VintageComics said:

What experience do you have in imaging? 

A great deal. Hardware exists to do this. Like anything it is expensive for quality, but this is not an AI issue. I've used this one - this is a medium-level non-destructive book scanner. You could do a comic book on here in maybe a minute at 600 DPI. A higher-end one would get much higher DPI at the same resolution.

On 12/26/2023 at 2:11 PM, VintageComics said:

How much do YOU think it would cost to implement a hardware system that could turn pages and image them to grade comic books

I have no idea but this would be essentially a one time expense and you are not creating from whole cloth. It already exists. Many companies do this already. 

On 12/26/2023 at 2:11 PM, VintageComics said:

Do you believe it would be cost efficient enough to implement in 12 months?

Yes.

On 12/26/2023 at 2:11 PM, VintageComics said:

Did you want us to stop discussing these things? 

No, but stop moving the goalposts. Can AI do this? Absolutely. Can it do it in a cost efficient manner quickly? If someone wanted to, sure.

On 12/26/2023 at 1:02 PM, VintageComics said:

One of my daughter runs a dental office. 

Again, not saying it's impossible. I'm saying it's not feasible at this point. 

How much does it cost? 

You didn't ask how much it cost. You asked if it could be done in an economically feasible manner. It is completely impossible to answer either of those questions because no one knows how much it would cost to purchase the hardware required - which has nothing to do with the AI - nor does anyone know what the actual software would cost. You are arguing an angels on the head of a pin argument that cannot be answered.

Based on my understanding of the technology, the software, and the implementation of AI across multiple industries, if a grading company wanted to use AI and wanted to invest in the hardware required that company would, after about 12 months at the absolute outside, have a grading system that could do many multiples of the throughput that grading companies do now at a significant cost savings. There would also be a very added benefit of no subjectivity in grading - the AI would grade everything the same. There wouldn't be the "Golden Age" bump, for example (unless that was built into the algos by the information at the beginning). 

On 12/22/2023 at 9:45 PM, VintageComics said:

I personally have stated many times that AI can do aspects of grading, but grading an entire comic is not going to happen anytime soon for a zillion different reasons, but the primary one being that you need to intersect the following

i) handling the actual comic book is complex

ii) time constraints - sure, if I had an hour to feed all my info into a computer I may be able to get a reasonably accurate grade, or grade range but you need this done in seconds

iii) cost constraints - how do you build something this complex, in a space that doesn't take too much room, is cost effective and accurate

iv) you will ALWAYS need some level of human interaction throughout the grading process, whether it's from receiving packages, to unpackaging, to laying them down on an assembly line, to removing them from Mylars, to grading them (flipping through all pages) to putting them back into Mylars, etc. so where does the human stop and the AI start and visa versa?

v) you need to TEACH the AI to learn along the way (or from past experience) - that's a stall every time you find a new problem to solve, and this happens daily when grading 1000's of books a day. For example, there are things that happen in the grading process EVERY DAY when weird defects, or a crossover of defects happen that need actual human conversation to make a decision. This will stall the grading process and needs to be learned and it happens daily.

vi) you'd need to make AI changes every time a new defect or variant is discovered - new learning curve

----------------------------------------

The way I see it the variables are myriad and not easy to solve. 

Humans do this sort of learning very quickly. 

I just don't see AI grading books accurately, in a cost effective and timely manner anytime soon. 

Thoughts?

This was your original post.

i) This isn't an AI issue, this is a hardware issue. Imaging hardware at a high level already exists and if there was a desire to do so, it could easily be implemented by a grading company.
ii) This shows a fundamental lack of understanding what AI is and does. If you 'feed all my info into a computer" the AI will learn. That's the whole point of AI.
iii) Not an AI issue, a hardware issue.
iv) Not an AI issue, HR and hardware issues, both of which could be addressed by a forward-thinking grading company.
v) Again, a fundamental lack of understanding of what AI is and does. The system learns. That's the whole point.
vi) Fundamental lack of understanding of what AI is and does. The system learns. That's the whole point.

The variables are myriad but the only one that isn't easy to solve is the hardware issue. AI will learn all of the variable, and AI learns at an exponentially higher rate than humans.

On 12/26/2023 at 12:28 PM, VintageComics said:

I didn't put a cost to it. I simply said it's still not feasible and is not happening anytime soon. 

You seem to contradict yourself here, because above you say it's not as expensive as I've suggested, and here you say we're not far off from achieving "economic equivalence".

What's far off?

So the question, which has stayed consistent all along through all the various threads and discussions is, when will it be economically feasible to implement at CGC?

 

We can't even have automated cars yet (although that's coming), which doesn't take a lot of fine, motor skill work. It's all macro stuff. 

We can't have robots perform surgeries without human control and involvement, which you yourself have stated. 

We can't even have basic robots deliver Uber food orders yet. I once saw one of those robots hit a street pole at full speed.

I personally believe we'll sooner have automated cars for the public, robot surgeons without human involvement and Uber eats vehicles that don't hit poles before we have robot graders at CGC. 

I don't think we'll see it within a decade. 

Roy - you keep moving the goalposts.

The three things you cite all have subjective issues. Grading is objective - or could be made to be - through AI.

When would it be economically feasible to implement? Within a year at the outside if they (1) had the hardware technology problems fixed to image pages (and that technology already exists) and (2) wanted to do so. Assuming the imaging issue - which should not be minimized - could be addressed to a satisfactory point, a grading company could increase throughput exponentially. 100% guarantee there will be AI grading of cards at a high level by the end of this year as the technology issue there doesn't exist.

On 12/25/2023 at 11:20 PM, MatterEaterLad said:

These books were graded 4 DAYS APART. Book was given a green label on a Friday, and is graded blue the following Tuesday.  There's no way that book left CGC.

 

That's not four days apart, that's one day apart - the book was done on Friday. One business day is Monday.

On 12/25/2023 at 2:25 PM, namisgr said:

I'd paraphrase you that since we can map brain function, we can map comic book grading.

As Donut has pointed out already, the robotics and image capturing are not examples of artificial intelligence.  Also, requisite technologies already exist for handling and imaging comics.

The part that CAHokie's post addresses is the role for machine learning.  Neuroscience has already successfully done the following with it: by implanting an ~300 microelectrode array on a part of the neocortex that oversees facial muscle movements that are required for speech, and using a machine learning algorithm to translate the ensemble of nerve cell activities recorded as a person thinks of speaking a syllable, a computer can be 'taught' to make speech for a person suffering facial muscle paralysis who has lost the ability to speak.  

Brain-reading devices allow paralysed people to talk using their thoughts

By contrast, it would be much, much easier to use machine learning and series of digitized images to develop a grading algorithm that could closely align with the comic book numerical grades assigned by a team of CGC graders.  Such a system would need development, and it may be awhile before the approach could be cost effective (i.e., cheaper per comic book than the cost per comic from a panel of graders).  But it's probably not decades away.

Decades? If someone wanted to and the economics were there you could do it within 12 months, based on the advances in the technology now.

On 12/25/2023 at 11:26 AM, Buzzetta said:

Already here.  The question is whether or not it can break the stranglehold that PSA or Beckett have on the market.   I could easily see one of the big two or CGC buying a company like this to gain the use of their tech and implement on a broader scale towards their own card grading, or in the case of CGC cards and eventually comics. 

https://agscard.com/

https://agscard.com/about

I would imagine that is in AGS cards' business model. Note that the automated grading part of what they're doing is easy as they appear to have solved the hardware issue.

On 12/24/2023 at 10:41 PM, VintageComics said:

Question 1) How do you capture head on images of pages unless you open the book 30-60 times at a 45 degree angle or greater?

Question 2) Who or what will do the opening?

Question 3) You'd need another 30-60 images of each page at an angle then?

Question 4) How much time do you foresee this taking just for one book?

These are not AI problems, they're hardware problems, but ones that could be initially handled through an human operator opening everything and imaging them. Imaging items in a high resolution and high-quality environment is not difficult. Google has been doing it for years and their systems are getting better and better.

None of the things you have talked about in this thread (or the other one) are AI issues. If someone wanted to find an econometric model that worked AND was willing to invest in fixing the hardware problem, AI grading of collectibles would be very quick to get to a very high level of confidence - its just learning and continual examples teaching the system how it works. Grading cards using AI is probably coming because the hardware problems would go away.

On 12/24/2023 at 11:06 AM, VintageComics said:

Just the topic of scanning and interpreting images, (and this post doesn't even touch on how the book will be manipulated for scanning) is pretty complex. 

The problem as I perceive it it isn't that AI can't just scan and read images, we all know it can, but a book is a 3 dimensional item. 

It's a combination of things like how will the book be delivered and show to the AI program / scanner?

Who will expose both sides of every page in a book (16 - 32+ wraps or 32 to 64+ pages?)

How far open do the pages need to be?

Can you scan them accurately at an angle?

Can you scan them accurately with curvature on the pages (meaning they aren't laying flat)?

How do you inspect staples? Especially in square bounds?

You're already imaging 32-64 pages, how do you image the sides of the book, like the open edge, the spine the tops and bottoms?

I've had books with defects ONLY apparent on the open edge of the book - literally across the face of the page ends. Really. I had a book where someone wrote in ink that only showed up in UV on the literal edges of the pages and the defect wasn't visible from the flat side of the page. 

This was one of those strange defects that I was talking about that you would have to completely retrain AI for once you uncovered a new flaw. 

Then we have the problems of stuff like specks of dust and other things that can corrupt images as discussed above. 

Every little new factoid is a learning curve for AI that would take countless hours to adapt to, that humans can factor in, in a matter of seconds through a personal discussion around a grading table. 

 

These are just some of the things that I've written "off the cuff" so to speak. There are probably a zillion others. 

 

I work for a firm that is pretty far out on the edge of AI so I'm pretty aware of what is out there because I'm trying to sell it.

Everything in this post can be easily fixed with data and changes. AI learns. That's the whole point. There is already AI doing things that were "impossible" 18 months ago and the curve is moving extremely rapidly.

If you think AI couldn't be adopted to grade comics, you're just flat out wrong. The reason why it wouldn't happen has nothing to do with the software/how it would work, it wouldn't happen because there's currently no economic reason to do it.

Picked up by local news. Textbook case of corporate clownage.

On 12/16/2023 at 9:38 PM, Tnexus said:

You also need 10k minimum to sell on Heritage.

No you don't.

My dude. Don't over think it. Your comic book is not a comic book, it is a widget. Sell it on the platform that gets you the most eyeballs with the lowest cost. Try to sell it here, but for a book like that I'd use Comiclink. 10% selling fee and they do a great job. It might get lost at Heritage.

Please enjoy and feel free to block supermario_84. I certainly did.

On 12/7/2023 at 11:46 AM, g-man said:

Hakes sold the 9.6 ASM #1 for over $500k w the juice....we thinking $750K for the 9.8 pedigree or higher? 

Easy seven figures.

Its just money. You can always get more.

Also monster books in January means no income tax paid on them until April 2025, for what that's worth.