Not a lot of shops these days are bragging about hand-writing machine code and a complete lack of automated testing. We had already automated so much before LLMs came into the picture.

Why would you brag abput this. Most places make perf products do not use llms to write all their code. This isnt rare. You people dont know much outside of webdev. There isnt a single defense outfit doing it lol.

Neither of those mentioned is an equivalent in any way.

Seems like a pretty large claim. Why does a binary exist here and not a continuum?

Humans aren't magical, so if people can figure out what maintainable code is and how to write it, so can a non-human. Furthermore, humans are rather unlikely to be the optimal form of intelligence for software architecture and engineering, so it's almost certainly the case that if humans can figure it out, some non-human could do it better. That it's not yet solved by models suggests that it's not easy and maybe even not practically achievable with current tools. But that's not the same thing as not solvable.

> Furthermore, humans are rather unlikely to be the optimal form of intelligence for software architecture and engineering

I like this framing. Humans invented software (and engineering in general) as a means to solve problems with methods that work best for us. There may be entirely different, and parallel, problem-solving methodologies outside of human best-practices.

And I think correctness for anything near the size of a CPU is off the table.

What does interpreting images mean in practice if you exclude the possibility of feature extraction or any other sort of implicit embedding?

I'm not an ML expert, but I was thinking of a sort of "guided" embedding. E.g., give the image model some prompt for what it's trying to do? I don't understand why multimodal models generate an embedding that doesn't understand what the model is trying to "figure out".

I think this is similar to how Gemma 4 12B is implemented, but even then I don't think the single layer image embedding is "aware" of the context.

You already do give the image model a prompt to tell it what to do. That’s not something the embedding can use independently of how the model is already using it.

In general an embedding doesn’t have intent or awareness in the way you’re looking for. “Embedding” just means one mathematical structure stuffed inside another. So for example the real number line is embedded into the Cartesian plane as each axis- that’s an embedding.

Now in this case specifically, the embeddings in any kind of transformer model encode the meaning of the thing they represent into vectors (which is what the model itself actually operates on). You can train the embedding to be more useful for a particular task at inference time, which already happens.

I think what I'm saying is that I don't understand why the embedding exists. I assume it's some kind of training and inference cost issue? But why can't the Gemma architecture linked above just learn to represent pixels in the LLM model's embedding space directly, rather than having the embedding from 48 x 48 pixel chunks? Or rather, give the embedding model some context to produce the embedding? (Which, as you note, wouldn't really be an embedding anymore, but seems like it would better understand fine detail)

Embeddings are used in language models to convert problems which are about words and meaning (which computers suck at) into problems which are about multiplying matrices, (which computers are really good at).

So embeddings are used in vision models to convert problems which are about the content and meaning of images into problems which are about multiplying matrices. The model doesn’t want to work with pixels (that’s what very basic vision models do, but it tends to be limited to special purpose applications) it wants to work with concepts in the image. That’s what the embedding gives it.

I still don’t really know what you mean about giving the embedding model some context. It embeds whatever you want to embed. So if you want to give it just a jpeg, fine. If you want to embed a jpeg and a json blob with some additional metadata/“context”/whatever, that’s also fine. That’s already how embeddings work.

Unless you’re making an especially boozy recipe, there’s not much alcohol in a reasonable portion size of tiramisu. I wouldn’t give it to someone strictly avoiding alcohol, but I’d have no concerns with a kid having some.

Do they do the same spying on the models/units produced for sale in EU? It’s not actually a necessary part of the operation of the device, so it makes sense they’d be able to sell them without it.

There’s no reason that sort of compliance needs an HOA. Most places already have building codes enforced by mandatory government inspections for major renovations.

It still does.

If casual use of profane and taboo words isn't offensive, are they really profane and taboo?

Non homogenous population response says both Yes and No

But it doesn't, strictly speaking, have to stop going. The bottom floor could be removed and placed at the top.