Check out mythic.ai for one example.

Please don't rely on my [inferior] explanation and search for yourself (start here for insance: https://www.google.com/search?q=what+is+compute+in+memory+an...). Asking about a new field is much better done with AI these days, because you can get it to explain just the interests and questions you personally have, rather than a generic and boring explanation.

In short, better than HBM is not having to move data in and out of memory at all or at least not as much. The compute part in inference is much simpler than the data hauling part.

Couple of examples: Check out Axelera's Europa board (upcoming) or their Metis board (existing). Or check out Mythic.ai which FINALLY managed to raise funds in Nov / Dec 2025. Ironically, her PhD thesis had been gathering dust before that.

With that out of the way, I think trying out developing software-building automation is a great learning experience, regardless of the final outcome. Beside [re]learning various ropes that might have been modernized recently, you are likely to end up with bonus [possibly tiny] helper tools that you can carry into your other software development projects. Or you might learn new [non technical] disciplines around software development life cycle.

- But that shouldn't be confused with getting the LLMs to make the decisions. I believe that would quickly ruin a good design, unless the decisions are about truly inconsequential aspects, which are very rare in language and API design.

- I don't believe that (sharing) is to the detriment of LLM providers either. Not realistically. We would build faster and the questions / research directed at LLMs would be more sophisticated. Believe it or not, they can't cache questions as easily as websearch queries. If anything, I believe the more people learn to use LLMs effectively (rather than just to generate slop), the more their usage will be ingrained in daily life. Some of that will be redirected towards current LLM providers. But perhaps more of the economic share will increasingly go to hardware providers, as more and more people will be interested to run their own models.

But are you claiming you eat the whole fruit, or you throw out the tiny thorn?

1. Free-form capitalism is fundamentally incompatible with AI. In other words, competent AI brings a free-form (low regulation) capitalistic environment to total collapse. (This is actually not my own opinion; heard the details from several economists and it makes sense to me).

2. Hiding from AI will not be an option for long. It will affect many jobs (often by increasing productivity at a macro level; it can reduce some productivity here and there, obviously).

3. The concerns about costs of energy (of the current applications) are short term. Follow major Electrical Engineering conferences to see why. In short, several ideas can drastically reduce the energy / token inference costs (some about 100x). Some existing companies are working on those ideas and at least one has a proof of concept (since 2018) and they raised capital to scale, late in 2025. Of course, once AI inference becomes cheap (in terms of energy per token), more hardware will be doing that, so overall I don't know where the costs will go. That is, new applications might become popular, using overall more tokens and eating through the "moore's law" of Inference energy.

4. The only way to prevent mass NEGATIVE disruption on state / country level is to HOLD THE SITUATION IN HAND and fully and consciously take it toward a good end state. Which needs GENIUS level analysis, insight, and execution, from the administration. Some countries are going to fare this better than the others.

But if you let LLMs talk to people (customers, for example) directly, then yes, you need an LLM provider that you can hold responsible.

That being said, I don't know what exact state the industrial automation technology is there and I can only extrapolate (or do websearch, which didn't lead to enough details; I only found things like https://www.youtube.com/watch?v=JnUGgc8R3ng).

When something like https://www.allegrohand.com is mass produced and used industrially, I bet the last mile (meter?) would change a bit, and full automation would be easier and less finicky.

The "AI CEO" problem is not fundamentally different from self driving car responsibility problems. You need a big entity to be on the hook (financially and legally) if you are really going for lowered responsibility on the decision machinery. I think it can work though (but with a LOT of effort), and that might be an interesting startup idea (we provide 90% of the CEO work via AI, you be in control of the remaining 10%, and responsible for maybe 20% of it; our "insurance" covers the other 80% of the responsibility).

I'm often okay if the answer is longer but not hiding the real answer; a couple of paragraphs that I can skim the answer from instantly is okay. When it really buries it I have to follow up to express the format and type of answer I want.

Of course, if you build up your prompt entirely by hand (copy pasting snippets, etc.) you can get away with markdown or plain text. That works okay for some harnesses, but it leaves too much control (or more accurately, opportunity to misunderstand) to the harness.