[giveita]

> v3 couldn't do this. No OR support. No complex boolean expressions. No parentheses for precedence.

This wasn't a minor limitation; it was a fundamental capability gap. Users were forced to learn ClickHouse SQL, write raw queries, and maintain them as our schemas evolved. We'd built a query builder that couldn't handle real-world queries.

What is it with the LinkedIn style?

No X

No Y

No Z

Isn't A its B

[outlier99]

It's not LinkedIn style, this is how ChatGPT generates text

[jjani]

It's not just ChatGPT—it's part of the inner fabric of Large Language Models.

Heh. But seriously, all frontier models do it, it's in the top 3 of tells that even someone with zero LLM experience can spot.

[ak_builds]

This article is part of our launch week and our main distribution channel is LinkedIn.

Our articles are now being read by stakeholders beyond our ICP.

I agree that LinkedIn/ChatGPT style isn't the best route. We cringe on it too. We are experimenting to find a middle ground between what gets more reach, while not giving into the trending writing styles.

Can I please get some more feedback from you?

- would you prefer more technical details in this article? - or just a change in the sentence structure that is more natural (like this response)? - or both?

[tux3]

The technical content is okay, but there's some fluff with a characteristic LLM signature that cheapens the whole thing. Instead of an article hand-crafted by human hands, it screams to the reader that they are currently reading slop.

I would rather not read other people's slop. I could pass your article through an LLM myself, if I wanted that. Here's just one of the most tired snowclones that current LLMs love, everywhere in your content:

>This wasn't a minor limitation; it was a fundamental capability gap

>context-switch not just between data types, but between entirely different mental models of how to query data.

>This wasn't something we asked them to do. They discovered that the query builder could now handle their complex cases, and they preferred it over raw SQL.

>That's not just a technical achievement. That's validation that we finally understood the problem we were trying to solve.

It wasn't just a minor stylistic issue; It was a signal to close the page.

[porker]

Isn't that though the narrative arc being shaped? We see it everywhere now, but just because LLMs like to output it doesn't make the structure you're highlighting bad.

Overall I found it a decent piece, a few too many "<term>: <explanation>" blocks for my taste but better than what I can write - and than most of the tech-industry blogging I come across.

[giveita]

Not sure why you need an "ain't just water, its a two element molecule!" type rubbish to tell a story.

[ak_builds]

Feedback well taken! I'll update the articles soon and do better henceforth.

[huflungdung]

…”for me”

Everyone else managed to read it fine.

[giveita]

Tropes in general I think become distracting. The ChatGPT style isn't bad in itself (just as one Giblhi cartoon isn't bad but 100000 are!)

But you could survey more people as maybe it is just me!

[giveita]

Agree with tux3 too