News for hackers. Stuff that matters.

xionplean

Re:Stable Cascade on Thursday February 15, 2024 @07:02PM (#39391108)
You obviously have no idea what you are talking about or just make stupid anime porn.

For fine art MJ destroys everything and it is even close. I say this with using comfyUI/SD all the time.

But you do you and your anime porn.

Re:Stable Cascade on Thursday February 15, 2024 @07:00PM (#39391086)
I use comfyUI/SD and MJ and I have never seen anything on the level of what I get out of MJ. Nothing at CivitAI is impressive to me next to what I get from MJ.

Of course, art is so subjective none of this has any real meaning. MJ routinely blows my mind though and it is very rare something from SD does. The secret MJ sauce is obviously all the human feedback that has gone into the model at this point.

I think AI video will be a different story though. I think that is when comfyUI/SD will destroy MJ because MJ is simply not going to be able to have an economic model with the amount of compute needed.

Re:What If I’m Wrong? (2023) on Thursday February 15, 2024 @06:27PM (#39390754)
It is hysterical to me that there is this online "go to Dunning and Kruger in the total wrong context" heuristic that people who don't know anything about the subject spit out.

If you understood Dunning and Kruger you would not post this not to mention make a Daniel Dennett appeal to authority case.

Re:Memory and new controls for ChatGPT on Thursday February 15, 2024 @06:17PM (#39390656)
IMO it is because there is a huge stochastic element to all this.

If we were all flipping coins there would be people claiming that coins only come up tails. There would be nothing they were doing though to make the coin come up tails. That is just the streak they had.

Some days I get lucky with chatGPT4 and some days I don't.

It is also ridiculous how we talk about this as if all subjects and context presented to chatGPT4 are going to be uniform in output. One word difference in your own prompt might change things completely while trying to accomplish exactly the same thing. Now scale that to all the people talking about chatGPT with everyone using it for something different.

In the US, the problem is we have built large offices around the idea of a central elevator shaft then the plumbing and bathrooms are running up and around the shaft. It makes perfect sense for a large multi story office.

You would have to design these weird apartments though that are like a thinly sliced pizza with no central area. Just a long hall of connecting rooms.

Or to retro fit all you have is the foundation and sides, everything else is basically wrong and cost wise you have less than nothing. It is just cheaper to start over and not have to undo all the wrong aspects.

We are mostly in denial in the US that there is going to be a ton of empty, useless buildings along with many regional banks going out of business.