gaazoh

> How open is bricks stack exchange to posting just an image of a brick with not much more to go on?

Judging by the 623 answered questions with the "part-identification" tag (out of 636)[0], I'd say pretty open. A lot of them are just what you are asking for, people helping IDing a single part from a picture. Some are much more specific, asking about minor variations on parts, and still get a detailed answer a lot of the time.

[0]https://bricks.stackexchange.com/questions/tagged/part-ident...

You can try to find the parts that stand out on bricklink[0], which will point you to the sets they were used in. It's pretty quick, once you figure out what the part can be called or what category it fits in.

If you can't figure it out, you can ask for help on the "bricks" StackExchange site[1].

[0] https://www.bricklink.com [1] https://bricks.stackexchange.com/

Very cool! The speed at which it auto-fills a grid is mesmerizing. Is this done server-side or client-side?

I sometimes build crosswords for fun, and I have tried some native building apps, but I didn't find one that's good for building French rule crosswords. The best I have so far is [this one](https://casevide.fr/creation/outil/), that's basically just a dictionary lookup and it's very slow (pure client-side JS), but still allowed me to build a handful of puzzles.

How hard do you reckon would it be to adapt your solver to work with French rules (no symmetry, 2-letter words allowed, minimizing black squares)? Or any other crossword style (French "arrow-words", British cryptic crosswords, Italian puzzles with no black squares but delimiters between squares...)?

Maybe I'll give it a try myself. What resources did you use for figuring out the algorithm? Is your source code available?

While I agree with the title, I find it very lackluster that it entirely focuses on some specific AI interfaces.

First of all, ChatGTP implies by its name that it's designed to chat. It's a sophisticated chatbot, but a chatbox nonetheless, you are not going to have a chat by filling a form. Then the examples given for StableDiffusion are not natural language. In this case, there can probably be a better interface than a single textbox, but the issue is the textbox, not that it expects natural language (it doesn't).

Other types of interface for AI stuff do exist. Copilot is also an LLM, but it takes surrounding code as input, not a natural language prompt. Plenty (most) of models take whatever format is convenient for the task and output an adapted format (image/video/text classification, feature detection...).

On the other hand, there are some interfaces that force natural language processing where it is one of the most unnatural and ineffective option, and no AI whatsoever is involved. Anyone who ever tried to book a train ticket in France in the past couple of years know what I mean[0]. Having to spell out an itinerary and date information is very, very confusing and error prone.

[0] https://www.sncf-connect.com/

This is hardly comparable to peace-not-war.

Peace-not-war was malware, or more broadly sabotage, this is merely a statement. While both are a form of protesting and stating political stances, one is usually illegal and widely rejected while the other is protected by the UN's declaration of human rights and by the constitution of any non-authoritarian country.