Amy is ‘any’ in witness protection. The downvoters put her there."

That procedure is called fascism.

Auto correct for any

Uh, idk, I’m not the one arguing for it either.

Oh so you just ignored any counter to your main argument and go on full confrontation while being very ignorant of your username as well.

Him. I think I’ll check out of this conversation. There’s no use talking to ignorants.

Before we to on to the next topic, did we establish that the environmental impact of AI is not really a concern for you anymore, and you used it as a scapegoat earlier?

Data centers can in principle be built environmently friendly (like mobility or heating, unlike air travel or animal farming) The reason none of these are concerned with environmental impact is that the whole US of A shits on the environment and has zero regulations for anything. There is the real issue, and avoiding data centers helps exactly nothing in the larger picture.

Don’t be hypocritical with singling out the one technology that you happen to dislike for other reasons.

Be embarrassed about falling for misleading misinformation. When concerned about environmental issues we have way way way larger issues to address than data centers.

For clarity, I don’t say their impact is nil, just that it pales in comparison. For example with industrial animal farming.

That’s a rather obvious and expected move in my eyes. After all, they had setup themselves for deep AI integration with their processor changes about a decade ago already. I was wondering for a while why they never really played their hand so far. Siri was not the epitome of that development.

What did you expect? I responded very on topic to the post, and you had no other response than to blow out your generic AI hatred.

Woosh, apparently. Let me explain.

LLMs are virtually nowhere used without some sort of harness these days, most prominently agent harnesses.

Skills are a harness artifact for reusable prompts where we encapsulate small terminology or large processes. People who use them quickly come up with or reuse a skill that will lead the agent to lead interviews to get a common understanding of key issues before going to action.

As for no 2, idk why that’s so relevant for automation. Often after an extensive interview the agent proposes solutions like I’d envision them, but much more thoroughly written out, in a quality and consistency that maybe a much reviewed and discussed RFC reaches, but I typically not. Sometimes it suggests solutions that I didn’t think of, but when poked it’s usually an elegant one. I don’t suppose the agent came up with these things itself, but it certainly has read many more books than I did, so that’s not objectable.

Username doesn’t check out.

And here I was merely wondering how they changed the counting rules.

And probably get it.

And that alone is worth a lot

don’t ask questions

Skill issue, in the most literal sense possible.

Sane people do. But the site is filled with AI haters who press downvote as soon as someone recommends using AI for Amy thing whatsoever.

Recently my Agent came back from a research task stating it had to complete various captchas but succeeded, then it reported the results.

OP said age verification via credit card is also possible.

Ah so you answered my question in this sub thread.

But that procedure doesn’t strike me as insensible. I honestly have more problems with a stance that expects companies breaking their contracts by default. I’m all for better controls where appropriate, but as a default stance this disallows you to do anything in our world. It’s just not possible to do anything if you say no to every contract that requires your identity.