Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Tips for 3D Work

davesnider.com

Post reply on HN
Print view View original

11–20 of 53 posts

Re: Claude Tips for 3D Work

#11

Post by sigmoid10 »

>I still occasionally hand write code in NeoVim on the bits I care the most about (CSS, design and early architecture like API patterns)

I find it amazing how people's opinions differ here. This is the first stuff I'd trust to Claude and co. because it is very much in-distribution for training data. Now if I had sensitive backend code or a framework/language/library that is pretty new or updated frequently, I'd be much more cautious about trusting LLMs or at least I would want to understand every bit of the code.

Re: Claude Tips for 3D Work

#13

Post by gbalduzzi »

sigmoid10 wrote: post #11

>I still occasionally hand write code in NeoVim on the bits I care the most about (CSS, design and early architecture like API patterns) I find it amazing how people's opinions differ here. This is the first stuff I'd trust to Claude and co. because it is very much in-distribution for training data. Now if I had sensitive backend code or a framework/language/library that is pretty new or updated frequently, I'd be mu…

I think the main point is that LLMs are pretty good at following existing patterns and conventions.

If you setup your skeleton in a way it is familiar to you, reviewing new features afterwards is easier.

If you let the LLM start with the skeleton, they may use different patterns and in the long run it's harder to keep track of it.

Re: Claude Tips for 3D Work

#14

Post by tonypapousek »

sigmoid10 wrote: post #11

>I still occasionally hand write code in NeoVim on the bits I care the most about (CSS, design and early architecture like API patterns) I find it amazing how people's opinions differ here. This is the first stuff I'd trust to Claude and co. because it is very much in-distribution for training data. Now if I had sensitive backend code or a framework/language/library that is pretty new or updated frequently, I'd be mu…

> in-distribution for training data

Engineers are an opinionated bunch, safe to say at least a small chunk of us will disagree with what goes into the training pile.

For me, it's preferring Deno-style pinned imports vs traditional require() or even non-versioned ecmascript import syntax.

Re: Claude Tips for 3D Work

#15

Post by bob1029 »

I've been having pretty good success with unity as a 3d llm tool. In addition to the iso views I've included a perspective mode that can focus on a list of game object ids with a custom camera origin. The agent is required to send instructions along with the VLM request each time in order to condition how the view is interpreted. E.g.: "How does ambient occlusion look in A vs B?".

The VLM is invoked as a nested operation within a tool call, not as part of the same user-level context. This provides the ability to analyze a very large number of images without blowing token budgets.

I've observed that GPT5.4 can iteratively position the perspective camera and stop once it reaches subjectively interesting arrangements. I don't know how to quantify this, but it does seem to have some sense of world space.

I think much of it comes down to conditioning the vision model to "see" correctly, and willingness to iterate many times.

Re: Claude Tips for 3D Work

#16

Post by Razengan »

Claude is terrible. I've been using Codex for a few months and decided to give Opus a try and see how it is.

After asking it to review a single file in a simple platformer game, it goes:

> Coyote jump fires in the wrong direction (falling UP with inverted gravity)

    var fallVelocity: float = body.velocity.y * body.up_direction.y
I'm like ok, suggest a fix

> I owe you a correction: after re-analyzing the math more carefully, lines 217–223 are actually correct — my original review point was wrong. Let me walk through why.

Oh boy. It's had several other gaffes like this, and the UI/UX is still crap (fonts don't get applied, it doesn't catch up with the updated working state after editing files etc.) Codex helped me save time but Claude is just wasting my time. Can I get a refund?

Re: Claude Tips for 3D Work

#18

Post by iLoveOncall »

gbalduzzi wrote: post #13
sigmoid10 wrote: post #11

>I still occasionally hand write code in NeoVim on the bits I care the most about (CSS, design and early architecture like API patterns) I find it amazing how people's opinions differ here. This is the first stuff I'd trust to Claude and co. because it is very much in-distribution for training data. Now if I had sensitive backend code or a framework/language/library that is pretty new or updated frequently, I'd be mu…

I think the main point is that LLMs are pretty good at following existing patterns and conventions. If you setup your skeleton in a way it is familiar to you, reviewing new features afterwards is easier. If you let the LLM start with the skeleton, they may use different patterns and in the long run it's harder to keep track of it.

> they may use different patterns

"Bad" is the word you're looking for, not "different".

Re: Claude Tips for 3D Work

#19

Post by OJFord »

sigmoid10 wrote: post #11

>I still occasionally hand write code in NeoVim on the bits I care the most about (CSS, design and early architecture like API patterns) I find it amazing how people's opinions differ here. This is the first stuff I'd trust to Claude and co. because it is very much in-distribution for training data. Now if I had sensitive backend code or a framework/language/library that is pretty new or updated frequently, I'd be mu…

I think OP nailed it with 'the bits I care the most about'—if you like those things a certain way, then you'll want to make sure they are that way, not accept whatever Claude does. If you don't care, you just want something done, then you'll have Claude do it while you work on what you do care more about.

Re: Claude Tips for 3D Work

#20

Post by NuclearPM »

iLoveOncall wrote: post #18
gbalduzzi wrote: post #13

Earlier quoted context omitted.

I think the main point is that LLMs are pretty good at following existing patterns and conventions. If you setup your skeleton in a way it is familiar to you, reviewing new features afterwards is easier. If you let the LLM start with the skeleton, they may use different patterns and in the long run it's harder to keep track of it.

> they may use different patterns "Bad" is the word you're looking for, not "different".

Different was fine.
Post reply on HN