[Timon3]

I think the important part from the article that establishes the difference is this:

> As I mentioned, in command-based interactions, the user issues commands to the computer one at a time, gradually producing the desired result (if the design has sufficient usability to allow people to understand what commands to issue at each step). The computer is fully obedient and does exactly what it’s told. The downside is that low usability often causes users to issue commands that do something different than what the users really want.

Let's say you're creating a new picture from nothing in Photoshop. You will have to build up your image layer by layer, piece by piece, command by command. Generative AI does the same in one stroke.

Something similar holds for your comment: you had to navigate your browser (or app) to the comment section of this article, enter your comment, and click "add comment". With an AI system with good usability you could presumably enter "write the following comment under this article on HN: ...", and have your comment be posted.

The difference lies on the axis of "power of individual commands".

[pavlov]

With a proper AI system you don’t even need to specify the exact article and nature of the comment.

For example here’s the prompt I use to generate all my HN comments:

“The purpose of this task is to subtly promote my professional brand and gain karma points on Hacker News. Based on what you know about my personal history and my obsessions and limitations, write comments on all HN front page articles where you believe upvotes can be maximized. Make sure to insert enough factual errors and awkward personal details to maintain plausibility. Report back when you’ve reached 50k karma.”

Working fine on GPT-5 so far. My… I mean, its 8M context window surely helps to keep the comments consistent.

[TeMPOraL]

Hey, that's cheating!

(I'm stuck with GPT-4 8k, still waiting for 32k API access. But one has to make due with what they have.)

[101008]

As the parent comment says, it's just another abstraction level. You have chosen a granularity, but even with "going to a website, enter your comment and click add comment" you are abstracting a lot. You are nto caring about connecting to a server, authentication, etc. The final user doesn't care about that at all, it's just telling the software to post a comment.

Right now the granularity may be "Comment on Hacker News article about UI this and this and that...", and in 100 years someone will say "But that's too complicated. You need to tell the IA which article to comment and what, while my new IA just guess it from reading my mind..."

[Timon3]

I guess you could also argue that telling another person 17 tasks to do is just another abstraction level. That doesn't change that it's a completely different interaction paradigm than the ones before.

[andsoitis]

> Generative AI does the same in one stroke.

But it isn’t creating what I had in mind, or envisioned, if you will.

[Timon3]

It might not be exactly what you envisioned, but that's where the difference comes in: with a batch processing system, you generate something over night with one input. With command processing systems you generate something with dozens or hundreds of individual commands, and it might still not be what you want.

With AI systems you generate something with one action, allowing you much faster iteration loops. Remember, the author argues that the current prompting still has bad usability. Presumably a system with good usability could allow you to generate what you want with one, or a couple, of attempts.

[throwuwu]

The current systems do let you iterate, that’s why they use a chat interface. Has everyone just been firing off a single request and then giving up if the first response isn’t perfect?

[Timon3]

The system lets you iterate, but you don't have to iterate to arrive at the result you want. Is that really so hard to understand?

There is no magic "paint the picture I want" button in Photoshop. There is a magic button in AI tools. This magic button does in one request what would take dozens or hundreds of commands without the magic button.

[krapp]

>This magic button does in one request what would take dozens or hundreds of commands without the magic button.

It very rarely does. And the more specific the request, the more work you have to do to get, at best, close to what you want. You may need to train your own model or blend models and mess with ControlNet. And then you have to do more work to fix stuff like fingers and eyes. In order to really use AI to its full potential (which still isn't, IMO, fully up to the capabilities of the software or artists it's intended to replace) you have to understand how it works, how the various filters work, how models work, etc.

Once you learn most of the really good AI generated art you find online is still heavily edited in Photoshop by actual artists you realize it's anything but magic.

[Timon3]

Come on...

>> This magic button does in one request what would take dozens or hundreds of commands without the magic button.

> It very rarely does.

No, it always does. You don't have to press the button 45 times in the morning and 67 times in the afternoon and 24 in the evening. You press it once, and you get a result.

What you read was: "This magic button does in one click what you want". That is not what I wrote, and not what the author argues.

> And the more specific the request, the more work you have to do to get, at best, close to what you want. You may need to train your own model or blend models and mess with ControlNet. And then you have to do more work to fix stuff like fingers and eyes.

Yes, you're repeating the author's point well: the current systems have bad usability in regards to how a user expresses their intentions. That does not change that the system produces one complex result with one button click.