I'm currently "working" on a toy 3d Vulkan Physx thingy. It has a simple raycast vehicle and I'm trying to replace it with the PhysX5 built in one (https://nvidia-omniverse.github.io/PhysX/physx/5.6.1/docs/Ve...)

I point it to example snippets and webdocumentation but the code it gens won't work at all, not even close

Opus4.6 is a tiny bit less wrong than Codex 5.4 xhigh, but still pretty useless.

So, after reading all the success stories here and everywhere, I'm wondering if I'm holding it wrong or if it just can't solve everything yet.

▲

shdh 36 minutes ago | parent | next [-]

I’ve noticed the models still can’t complete complex tasks

Such as:

Adding fine curl noise to a volumetric smoke shader

Fixing an issue with entity interpolation in an entity/snapshot netcode

Find some rendering bugs related to lightmaps not loading in particular cases, and it actually introduced this bug.

Just basic stuff.

	▲	computerex 5 minutes ago \| parent [-]
		They are definitely behind in 3D graphics from my experience. But surprisingly decent at HPC/low level programming. I think they are definitely training on ML stuff to perhaps kick off recursive self improvement.

▲

neomantra 6 hours ago | parent | prev | next [-]

While I’ve had tremendous success with Golang projects and Typescript Web Apps, when I tried to use Metal Mesh Shaders in January, both Codex and Claude both had issues getting it right.

That sort of GPU code has a lot of concepts and machinery, it’s not just a syntax to express, and everything has to be just right or you will get a blank screen. I also use them differently than most examples; I use it for data viz (turning data into meshes) and most samples are about level of detail. So a double whammy.

But once I pointed either LLM at my own previous work — the code from months of my prior personal exploration and battles for understanding, then they both worked much better. Not great, but we could make progress.

I also needed to make more mini-harnesses / scaffolds for it to work through; in other words isolating its focus, kind of like test-driven development.

▲

lukan 10 hours ago | parent | prev | next [-]

" or if it just can't solve everything yet."

Obviously it cannot. But if you give the AI enough hints, clear spec, clear documentation and remove all distracting information, it can solve most problems.

	▲	shdh 35 minutes ago \| parent [-]
		Most simple problems with plenty of prior art, sure

▲

layer8 7 hours ago | parent | prev | next [-]

My impression is that it always comes down to how well what you’re trying to do pattern-matches the training set.

▲

embedding-shape 6 hours ago | parent [-]

When it comes to agents like codex and CC it seems to come down to how well you can describe what you want to do, and how well you can steer it to create its own harness to troubleshoot/design properly. Once you have that down, I haven't found a lot of things you cannot do.

▲

layer8 6 hours ago | parent [-]

Breaking down and describing things in sufficient detail can be one way to ensure that the LLM can match it to its implicit knowledge. It still depends on what you’re trying to do in how much detail you have to spell out things to the LLM. It’s almost a tautology that there’s always some level of description that the LLM will be able to take up.

	▲	embedding-shape 4 hours ago \| parent [-]
		Well, not just breaking down the task at hand, but also how you instruct it to do any work. Just saying "Do X" will give you very different results from "Do X, ensure Y, then verify with Z", regardless of what tasks you're asking it to do. That's also how you can get the LLM to do stuff outside of the training data in a reasonably good way, by not just including the _what_ in the prompt, but also the _how_.

▲

seba_dos1 10 hours ago | parent | prev | next [-]

It works somewhat well with trivial things. That's where most of these success stories are coming from.

	▲	shdh 34 minutes ago \| parent [-]
		Exactly this, the SNR is polluted by this anecdata because someone was able to implement a CRUD backend they couldn’t before

▲

nothinkjustai 2 hours ago | parent | prev | next [-]

Nah, it only lives up to the hype for crud apps and web ui. As soon as you stop doing webshit it becomes way less useful.

(Don’t get mad at me, I’m a webshit developer)

▲

wg0 8 hours ago | parent | prev [-]

Most of the folks are building CRUD apps with AI and that works fine.

What you're doing is more specialized and these models are useless there. It's not intelligence.

Another NFT/Crypto era is upon us so no you're not holding it wrong.

▲

MattRix 4 hours ago | parent [-]

This is pretty wrong. Anyone who thinks this stuff is similar to NFTs and crypto hasn’t been paying attention.

	▲	73738488484 2 hours ago \| parent [-]
		Indeed this time it's different