I'm not a native English speaker, but have been reading and sometimes speaking English for decades. For me 'the ask' feels strange. It sounds like it's just a verb made into a noun, like saying 'the sing' or 'the eat'. "I had an eat" "Three asks".
What would make someone want to write 'the ask' and not 'request' or even just 'question'? How is it different?
What's your point? Don't use LLM for CMS content? That my code is buggy? Or that people shouldn't trust the LLM they run on their computer on their own website?
You can check the code for exploits yourself. And other than that it's just your LLM talking to your own website.
> Also why bother with wordpress in the first place
Weird question, but sure, I use WordPress, because I have a website that I want to run with a simple CMS that can also run my custom Wordpress plugins.
It seems your link about the Wordpress variation validated my idea :).
If the new Wordpress feature would allow for connecting to Ollama, then there is no need anymore for my plugin. But I don't see that in the current documentation.
So for now, I see my solution being superior for anyone who doesn't have a paid subscription, but has a decent laptop, that would like to use an LLM 'for free' (apart from power usage) with 100% privacy on their website.
The essence works, I was able to let it make a simple summary on CMS content. So next is making it do something useful, and making it clear how other plugins could use it.
> I could trigger it in a pc. I'm not sure if it's useful.
I made this long-press rectangle selection, because the whole silly face app, was an experiment actually for a UX tool (https://www.producthunt.com/products/tinyux) from a couple years back. It makes more sense in that context.
I removed it from Google Play. May end up making a web version out of it.
> [Hi from Argentina!]
Hi, from Netherlands
> * In the main screen, the grey rectangle is not aligned with the other rectangles.
Very unclear on my part, but if you draw on the grey part (an eye for instance) it will 'hang on it'. So it's like background. I wanted to have some background in there from the start so people could discover it. Presumably that is what you are referring to? Tap multiple times on the brush next to the '?' to toggle foreground/background.
Or there is visual bug.
> The white rectangle cleans the eyes/noses/whatever/ but it does not clean the skin color.
Ah, yes, that was an experiment from just this morning. The idea is that empty cells 'grow' this skin based on the neihbors. So you can't clean empty skin.
I'd like to have more things like that, so it more 'grows' and less draws. But could also be annoying feature.
> Also, perhaps the grey rectangle probably should cycle like: nothing->grey->red->dark->pink->nothing->grey->... Or skip the "nothing" color in the list, but make the white rectangle delete the color.
Perhaps so. I'll think about it.
> When I use the grey rectangle tool over an eye or something, it may change to another eye. I prefer that they change only when I use the eye tool over and eye. I expect the grey rectangle tool only to change the color, not the shape.
It's like a background. Try some brushes around the edges..
> I don't like that the nose rotate when it's grey and some of the nearby squares are aso grey. It's too unpredictable. I'd prefer that using a nose on a nose will sometimes change the shape and other times rotate it, so I can click on it until I get the shape I want.
I guess it's about control versus a game where you discover stuff.
I made it with more of game/toy perspective (and a technical prototype for the UX tool). So you discover new brushes, and I wanted the interface also to be easy to start, but you could get 'good at it'.
I could then show you a silly face image, and it would be somewhat of a challenge, like a show-off "Look how good I can play with this", where you see the face wear a crown, etc.
for instance there are many brushes to discover by combining them. round-ear with mouth will get you flower. Tap mouth again, you'll get a different flower, etc.
For now I'll keep this approach. But in the UX tool I ended up making sub-menus so you could simply select what you wanted. Much simpler haha :D
Ah, yes, this worked in the app, not really on the web version yet.
It meant to say: long press will allow you to paint in a rectangle. So long press one corner, then press another corner.
I'll look into if I can fix that.
Btw, my goal was to have zero language in the app, so I wouldn't have to make any translations, and it would just work for kids of any age. Hence the somewhat weird '?' popup.
Might turn this into a thing where you can download a PDF of the image, and you can print and can cut it out and fold it into a brick shaped character. As in; top half face, bottom half rest of body.
Update: I adding a 'eyes spotted' (round nose + eye) and a 'skin effect' when empty cells are near some things, they change too. Spots or scales for now.
Looking from the outside, there are no MAGA views, it's just whatever Trump says. What should be the AI's view on international wars for oil or ego?