And this is fine. Developing new software with a really smart intern is the same, you, as an expert, need to bring your experience/expertise on the table to have everything right. Because experience needs time.

Quarto is my documentation tool.

For me, they are both massively used, but cover different usages.

[0]: https://www.britannica.com/place/Le-Creusot

[1]: https://en.wikipedia.org/wiki/Le_Creusot

I cannot tell if the alternative solution will be better, but I do think we will develop alternatives.

- I wonder, is it possible to give a reason to the flag?

- Is flagging the submission without comments the right way to go?

For me, it is important that slowly but surely it goes through that AI slop is not what is accepted here on HN. Yes to have whatever LLM helping with grammar, spelling, etc. but the content should not be the output of a one shot "write me a blog post about humanoid robot actuators" prompt.

[0]: https://news.ycombinator.com/item?id=48005917

[0]: https://en.wikipedia.org/wiki/Slide_rule

Still, one thing I really like with LLM/AI, is that now, I can allow myself to test different abstractions a bit faster. I can allow myself to "try" more complex refactoring on a feature branch, because if I describe correctly the abstraction I want, the LLM/AI tool will be normally good at producing it. But to describe my abstraction, I need to pull all my programming and engineering years of experience.

But at the end of the day, I always tell my wife, that with these new tools, which I could not imagine so powerful 3 years ago, I live in the future :-)

The only change in my workflow is that now, I am also using in parallel a stupid command line tool "vibe coded" in Python to read my emails. It allows me to quickly check my emails out of VS Code in a Claude Code session, a bit like when I was doing my emails directly in Emacs :-)

Here, they put limits on the "under-cover" use of the subscription. If they can provide a relatively cheap subscription against the direct API use, this is because they can control the stuff end-to-end, the application running on your system (Claude Code, Claude Desktop) and their systems.

As you subscribe to these plans, this is the "contract", you can use only through their tools. If you want full freedom, use the API, with a per token pricing.

For me, this is fair.

The analogy is that each layer is a slice of Emmental cheese. You end up with a bad event, only if all the holes in the slices align.

I spend a couple of hours per week teaching software architecture to a junior in my team, because he has not the experience to not only ask correctly but also assess the quality of the answer from the LLM.

So sorry but no, the platforms are addictive and not all the kids can resist against an armada of statisticians ensuring the systems stay addictive only through honest conversations.

By the way, this would mean you could solve all the addiction issues if it would be working...

[0]: For me this is really an important part of working with Claude, the model improves with the time but stay consistent, its "personality" or whatever you want to call it, has been really stable over the past versions, this allows a very smooth transition from version N to N+1.