HN user

crashprone

13 karma
Posts0
Comments13
View on HN
No posts found.

You seem to have posted your polite question as a reply to the bot comment which talks about PR #1484 and not your PR. I'd say it's pretty obvious why the maintainer thought you were pushing the bot's PR.

As someone else pointed out cooler heads and less passive aggressive responses would've resolved this issue easily.

Music Discovery 5 months ago

Exactly. The generic design is also such a turn off that I lose incentive to explore it's functionality.

A while ago, a HN comment linked to this blog by Mario Zechner https://mariozechner.at/posts/2025-06-02-prompts-are-code/ which was exactly what I needed back then. The workflow helped me analyse about 300 files. It definitely made up stuff along the way and missed valuable context that I would have seen had I done the analysis manually, but it's a good starting point.

Without a structured workflow, as you said, after 5 files, it's starts going berserk.

That said, Claude has been really bad the last few weeks, especially in VSCode Copilot. If you ask it repeatedly, it admits that's its Sonnet 3.5 and not Sonnet 4. Not sure if it's true, but Sonnets workflow has degraded the last few weeks.

You would get better results probably by using search and replace or a python script to make those changes.

The comments that insist you'd get better results by talking to it like you would to a human, I hope they're trolling. The idea that the tone of your prompt has any influence at all, is laughable.

You could've skipped the first 2 sentences, started with the third and finished with one more explaining why Lidarr is not a good solution. I was able to find a blog by joekarlsson which echoes your sentiment, is the album first architecture that makes Lidarr a bad choice? Any alternatives you'd recommend?

Hey sorry I missed these links when looking at the exercises. I guess anyone who is interested in actually understanding the concepts will click on the Learning tab and be led to those resources. As a user I would like to be inspired by what's possible with shaders, so I would prefer to have links to various ShaderToy examples on the homepage. However, that's just me, maybe others might find it overwhelming and prefer the simpler, easy to grasp examples. Thanks for your response to my feedback, wish you both the best for your product!

The idea is amazing, congratulations on getting the product out! However, there's a lot about this site that doesn't sit well with me. The rather generic site design and uninspiring results of the challenges are something that I could probably overlook, but what irks me the most is the lack of any human aspect throughout the site. How does an academy completely gloss over the contributions of various amazing people who've been teaching shaders for years now and are responsible for making shaders accessible and fun? I would've never learnt what GLSL is, without ShaderToy. If someone started learning shaders through this site and never discovered the treasure trove of material on iquilezles' website, how do we expect them to jump straight into "Ray Marching"? I can't help but think that the site intentionally holds back information on various other phenomenal shader learning resources.

Existing works of art like iquilezles "Planet Fall" should be part of the recommended curriculum if only to inspire others and set the baseline for what's possible with shaders.

Bait : "For 200$ a month you get to use Claude 20x more than what the Pro users are entitled to. You don't know how much exactly though, but neither do we. We may limit your usage with weekly and monthly limits. Sounds good?"

Switch: "We limited your usage weekly and monthly. You don't know how those limits were set, we do but that's not information you need to know. However instead of choosing to hoard your usage out of fear of hitting the dreaded limit again, you've kept it again and again, using the product exactly the way it was intended to and now look what you've done."