The output is not of high quality. It is extremely verbose for what it is trying to say, and I found myself skimming it while dealing with

1. The constant whiplash of paragraphs which describe an amazing feature followed by paragraphs which walk it back ("The shift is subtle but significant / But I want to be clear", "Kiro would implement it correctly / That said, it wasn't completely hands-off", "The onboarding assistance was genuinely helpful / However, this is also where I encountered", "It's particularly strong at understanding / However, there are times when");

2. Bland analogies that detract from, rather than enhance, understanding ("It's the difference between being a hands-on manager who needs to check every detail versus setting clear expectations and trusting the process.", "It's like having a very knowledgeable colleague who..."); and

3. literal content-free filler ("Here's where it got interesting", "Don't let perfect be the enemy of good", "Most importantly / More importantly"), etc etc.

Kiro is a new agentic IDE which puts much more of a focus on detailed, upfront specification than competitors like Cursor. That's great. Just write about that.

The words-to-thoughts ratio is way too high, it reads like a elementary school book report, it’s way too long for how dry it is, I could go on but these are just some of my initial thoughts while reading the article. Also, knowing it is mostly written with AI, how do I know if details are real or made up? There’s a reason you are reading my comment: it expressed thoughts or an image that you found captivating. Being able to write well is a privileged skill that improves your communication, ability to express ideas, your humor; the things that make you an interesting person. You should not be outsourcing your voice to AI. Also Spielberg wasn’t writing an article - he was directing a movie.

So we can debate the quality of this particular article, but in general if an author closely instructs the ai what to write, edits it, and uses the ai to express his thoughts faster and better, I have no problem with the use of ai as a tool to write better.

You’re making assumptions on the quality of the article just because it’s written with the help of ai, I think that not justified in general.

This article has the tell-tale signs of AI slop. It’s perfectly fine to use AI to write, but if you don’t know how to write well (which you learn by writing a lot and getting feedback), then you are just going to produce slop. And no I’m not making assumptions I’m making observations based on my experience reading AI generated text.

I personally really enjoyed that writing style and didn't notice any "slop".

I appreciate that!

Author here, and I mostly agree with this sentiment. With that said, part of my Kiro spec here, had Kiro read my other blog posts and attempt to emulate my style.

I too found the write-up to be a little dry and long-winded, even though the same critique might be leveled at myself [hopefully to a lesser extent]. I did feel like it was a good step up from the usual AI slop out there, and served to illustrate Kiro's capabilities.

I suppose in this context, I wanted to see whether I could take my reader on a journey long enough for them to be surprised by the AI reveal at the end. I'm not sure whether it achieved that but that was the artistic intent of this specific piece.

It's not high quality output when an opinion based article isn't written by its author. It's fiction.

It’s objectively not fiction, whatever it is.

Thumbs up to this concise comment, but I'd not even honour the blog author by calling it fiction. Probably more of a hallucination.

Where is the line?

Is it not high quality output when a ghost writer writes someone’s work? Can I use a thesaurus? What about a translator?

As long as the person who is putting their name on the article has provided the ideas and ensures that the output matches their intent, I see no reason to draw arbitrary lines.

Thesaurus: Sure, since you're looking up words but using your own brain to decide whether a word is appropriate or better. Caveat: some authors just throw in words to look smart. Concordedly.

Translator: Only if it's not creative writing and only if the output doesn't need to be accurate / there is margin for error.

Granted, the line is hard to place - see also the other post about where the line for adult content should be. But the thing is, when writing is AI generated, how can you know for sure that all the output was actually read and verified by the author? And text is not that important, but what about code?

The other argument: if an author didn't take the time and effort to write something, why should I take the time and effort to read and understand it? This applies to poorly written content as well. Ironically, a lot of people will already feed this article (and this comment) into an LLM to summarize it, if not to help them form an opinion about it. Summarizing isn't new though, there were tools some years ago to summarize webpages already.

Well, you just answered the question yourself, by inadvertently using a good example.

You see, a movie is fictional work, but a blog article most likely isn't (or shouldn't). In this case, I am reading the article because I want to know an objective, fair assessment of Kiro from a human, not random texts generated from an LLM.

It matters as its not about a vague notion of a "level of quality". It's about reading about a personal experience written by an actual person. It's about not insulting the intelligence of one's readers by throwing up a wall of LLM-text and signing oneself, it's about not being intellectually and morally dishonest by kinda mentioning it, but only half-way through the text. The comparison with Spielberg is almost there, but not there yet, as the director does whatever it is the directors do - not outsourcing it to some "Kiro". The right comparison would have been if the AI created the next sequel of E.T., Gremlins or whatever it was that Spielberg became famous for. Who cares? I want new and genuine insights that only another human can create. Not the results of a machine minimising the statistical regression error in order to produce the 100th similar piece of "content" that I have already seen the first 99 times. I have a feeling that none of the ghouls pushing for the AI-generated "content" have ever tryly enjoyed the arts, whether 'popular' or 'noble'. Its about learning something about yourself and the world, trying to graps the author's struggles during the creation. Not about mindless consumption. That's why it matters.

> I want new and genuine insights that only another human can create.

I’m not sure that’s true in an iron-clad, first-principles way. I think that many of the insights created by humans are combinations/integrations of existing concepts. That category of insight does not seem to require carbon-based reasoning.

I don’t claim that it can be achieved by statistical text generation, but I doubt the typical blog author is creating something that forever will be human-only.

Who knows, perhaps you're right? But in the meanwhile, I don't want a Kiro sharing with me fake experiences a Kiro never had.

> It's about reading about a personal experience written by an actual person

This seems to be the dividing line in the AI writing debate.

If one cares about the interpersonal connection formed with the author, generally they seem to strongly dislike machine-generated content.

If one cares about the content in isolation, then generally the perceived quality is more important than authorship. "The author is dead" and all that.

Both points are valid IMO. It's okay to dislike things, and it's okay to enjoy things.

> I want new and genuine insights that only another human can create.

This is a good illustration of what I mean: you personally value the connection with the author, and you can't get a human connection when there was never a human to begin with.

If you take a look at the others in the thread who had a positive view of the work, they generally focused on the content instead.

It's more that a human author has had an experience and writes to communicate it to other people. They have objectives that make sense in human contexts. They have learned things, run into issues, solved problems, developed arguments, evolved their understanding, felt emotions, considered and rejected actions, and integrated those recent experiences into a lifetime of experience. Then they order and condense all of that into a form that communicates it effectively to other experiencing beings.

LLMs, in contrast, experience nothing. When they "write", they are not even vaguely approximating what a human writer does.

I’m pretty sure Mr Spielberg DOES something. If he does absolutely nothing, I really doubt the phrase “directed movie indicates a level of quality” can have any level of truth in a general case.

Ai is just another tool, it doesn’t do anything by itself, in the hands of a person with a great story it can be a great tool to help write it. In the hands of a bad writer it will probably just create bad content. Ai is a tool controlled by a person.

Bullshit is what we call it when a speaker wants to look good saying something but doesn't care if what they say is true. It's a focus on form over content.

You’re making assumptions that aren’t grounded in facts, you do not know if they didn’t care, and if the blog contains fiction. He may have checked and corrected every single line created by the ai.

I was only responding to a philosophical question about what's problematic about putting someone else's work under your own name, not making an accusation.

To respond to you though, yes that is possible, but anyone who put in that level is work is highly unlikely to credit the AI as a writer.

And anyway, I had (and have) a choice. Plenty of people are still using their own words and have (or are building) confidence in their own voice, so those are the people I seek out because by giving them support I help make the world I want to live in

If they can't be bothered to write it, I can't bothered to read it.

It's more like if Spielberg produced a documentary about himself.

I would actually rather read his incomprehendable notes, and then the actual prompt he tried to send to the LLM, then skip reading the resultant generated part. This is actually what is worth reading to me