All those are certainly possible. I’ll see if I can get them added shortly.
Edit: I've added those features.
I actually changed it so that the preview you see is that actual image that gets exported. I like this better but it means that you'll get a little prompt for the text instead of editing it in place. I think it's a good compromise.
I'm a self-published author. This is the default setting for new books uploaded without DRM. It's gated behind an "I understand" checkbox. I plan to allow my books to be downloaded as PDF and ePUB.
Technically, yes, but Amazon customers probably wouldn't benefit from that. I don't currently distribute or sell books directly because that creates a tax burden. So it's probably best to let the various stores handle it. I still want to sell books but I don't want my readers to be restricted by DRM for a book they paid for. The honor system is fine for me.
Edit: I now realize you might mean in the Amazon KDP UI. I don't see a way to upload your own.
As an independent author you can do what you wish. The only restriction is if you are in the Amazon KDP select program then you have promised Amazon exclusive use for a cut of the Kindle Select pie. I also distribute my books on all the other platforms, and for my free sci-fi book host it direct on my web site and on my Ko-Fi shop (the 'buy-me-a-coffee' site). Selling directly and collecting money requires a bit too much work but technically you could do it.
I haven’t looked yet but I might be a candidate for something like this, maybe. I’m RAM constrained and, to a lesser extent, CPU constrained. It would be nice to offload some of that. That said, I don’t think I would buy a cluster of Macs for that. I’d probably buy a machine that can take a GPU.
I’m not particularly interested in training models, but it would be nice to have eGPUs again. When Apple Silicon came out, support for them dried up. I sold my old BlackMagic eGPU.
That said, the need for them also faded. The new chips have performance every bit as good as the eGPU-enhanced Intel chips.
eGPU with an Apple accelerator with a bunch or RAM and GPU cores could be really interesting honestly. I’m pretty sure they are capable of designing something very competitive especially in terms of performance per watt.
They are inseparable for Apple. CPUS/GPUs/memory. They can use chipsets to tweak ratios, but I doubt they will change the underlying module format—everything together.
My suggestion is to accept that format and just provide a way to network them at a low level via pci or better.
I had a similar result trying to create 16 similarly styled images. After half a dozen it just started kicking out the same image over and over again no matter what the prompt said. Even the “thinking” looked right, but the image was just a repeat. I don’t know if this is some type of context limitation or what.
I got around it by using a new prompt/context for each image. This required some rethinking about how to make them match. What I did was create a sprite sheet with the first prompt and then only replaced (edited) the second prompt.
I still got some consistency problems because there were a few important details left out of my sprite sheet. Next time I think I’ll create those individually and then attach them as context for additional prompts.
Oh smart. This is good guidance. Yeah fascinating how longer running context causes these side effects, especially the repeated image with no changes bug.
There is no wrong way to open the door. Any suffering on the owner's part is caused by the manufacturer building the car that way. A car like that clearly isn't meant to carry untrained passengers. If the car owner insists on buying an unsuitable car, then that's on the owner. It's no different from buying a two seat sports car as a family of four.
LLMs are already pretty good at brute force security testing. They aren’t “polite” pen testers.
I recently used an LLM to win a CTF at work (there were no rules against AI, but I bet there will be next year). I felt a little bad, at the end, when they demoed the intended hacks and, for a couple of them, it was the first time I saw the home page. If it could quickly hack it with just the clue and URL I just let it.
For any serious website it needs a lot more direction, but it will help you along nicely.
I only saw denials twice, over an entire week, and I used three different major LLM agents (Codex CLI, Claude Code CLI, and Gemini CLI).
It took time, I spent something like 20 hours guiding, but if you have the time, and some expertise, the tools are extremely workable.
Edit: I've added those features.
I actually changed it so that the preview you see is that actual image that gets exported. I like this better but it means that you'll get a little prompt for the text instead of editing it in place. I think it's a good compromise.
I also added a checkbox for making it animated.
reply