kikkupico

wow

Reminds me of the time Kasparov said playing chess against a supercomputer felt like facing an alien opponent.

The Blender connection - https://github.com/kikkupico/ambientcss/blob/master/ambient3...

The threejs scene in the docs is only for explaining the setup; it doesn't have a raytracer to render shadows accurately. The reference renders for the CSS were done in Blender. See https://kikkupico.github.io/ambientcss/ambient-css/grounded#... for examples.

With the knobs, I just figured out the problem was a stray div from an earlier version of the app overlapping the knobs in the components section of the demo app. I've fixed that now. Checked in both desktop and android Chrome and looks ok. haven't tested in mobile safari yet.

P.S: I agree knob controls in general are terrible UX. A real knob is usually turned with two fingers and the way on-screen knobs are operated is nothing like that.

Orthographic projection was chosen here deliberately - that's why elevation makes no difference to the size of the object but changes the shadow. Perspective projection won't work well with scrolling because the angle of the object would have to subtly change when the user scrolls. Orthographic projection doesn't need to handle that.

The docs have a page where the lighting and camera setup is explained with an actual threejs 3d scene - https://kikkupico.github.io/ambientcss/guide/concept/#how-it... . Hope it helps!

Regarding the textures, they respond to lighting but not especially well. In the demo app, you can scroll to the materials page and use the theme switcher at the top to see how the texture respond.

Contrary to the general opinion, I feel that AI has IMPROVED my cognitive skills. I find myself discovering solutions to problems I've always struggled with (without asking AI about it, of course). I also find myself becoming much better at thinking on my feet during regular conversations. I believe I'm spending more time deep thinking than ever before because I can leave the boring cognitive stuff to AI, and that's giving my mind tougher workouts and making it stronger; but I could be completely wrong.

> The point I’m making is that determinism isn’t the key difference between compilers and LLMs

I think you misunderstood. Determinism is the the difference between natural language and code. It's not about LLMs vs compilers.

> C code admits many assembly interpretations and the assembly you get will vary depending on your compiler and parameters.

There's your own example defining how code is deterministic. Despite being compiled to different assembly interpretations, the code does the same thing.

Natural language is fluid and ambiguous while code is rigid and deterministic. Spec-driven development appears to be the best of both worlds. But really, it is the worst of both. LLMs are language models - their breakthrough capability is handling natural language. Code is meant to be unambiguous and deterministic. A spec is neither fluid nor deterministic.

Wow! I just wrote the article "Stop trivialising AI: it’s not your intern, colleague or compiler" today and shared on HN - https://news.ycombinator.com/item?id=47274213 - but I talk about different dangers though. Enjoyed reading your viewpoint.

Fair enough! Business and user perspectives are meta-data that explain the intent behind the code. I disagree with the point that intent should be the source of truth, though. Intent, like you explained, is high level and lacks the details to be an unambiguous source of truth.

> You can argue that you can just ask the LLM to explain back and forth but it can still be too much.

But then you'd get an explanation tailored to your specific perspective instead of a generic one, right?

What do we gain by maintaining a high level view instead of asking an LLM to explain the code at a high level when required?

Thanks for the feedback! I agree there needs to be visual indication for the knobs' min and max points. I'm thinking about how to do this without adding visual clutter.

Thank you! I just changed the knob control gesture/drag logic and it doesn't work like a vertical slider anymore.

Made the knob controls more intuitive now. Please check it out!

Thanks for the feedback! Click and scroll up/down to turn the knobs. I will fix this as it isn't an intuitive way to control knobs. EDIT: Done! Please disregard this comment.

Exactly! LLMs' (or any Gen-AI) lack of lived-experience/emotions is their Achilles heel. The best human creators understand how to inspire emotions mainly because they can feel it themselves. Most other humans, despite innately understanding emotions, can't really create things that inspire emotions in others. So, Gen-AI as we know it today can't really reach a point where it deeply, personally understands and inspires emotions. Vibe discovery bridges this gap, I think.

There was a very specific purpose here - to build a web-based accelerometer game. If I were to compare this with playing, I would say this is more akin to playing with a special kind of clay that shape-shifts itself based on your instructions.

As for the LLM-generated writing - I've updated the blog post with a 'meta' section explaining how LLMs generated the post itself. I've shared the link to the specific section as a response to other comments with the same criticism - I don't want to link to the blog again here and risk looking like a spam bot.

Thank you for the honest feedback! I'll stick to writing content by hand for future blog posts.

Here you go - https://www.kikkupico.com/posts/vibe-discovery/#the-meta

The blog post was written by Claude Code, reviewed by Gemini Pro, ChatGPT 5.2 Thinking, Kimi K2 Thinking, Deepseek Deep Thinking and me. Naturally, all the LLMs failed to judge that AI-generated writing is a turn-off for most readers. I failed to judge that too.

I misjudged the amount of dislike HN users have for AI generated writing. I have added a "meta" section explaining how the post itself was written by AI, directed by my own taste. Here's the meta - https://www.kikkupico.com/posts/vibe-discovery/#the-meta

To be frank, I don't think AI-generated writing is inherently bad. Since there appears to be a strong bias against it, I will stick to writing blog posts by hand.