Hacker News Reader

moonuon Ask HN: Is "3D as software" about to undergo a Cambrian Explosion?

This is an interesting question where the answers feel tied to the training data, because with 2D, you primarily have declarative data with HTML/CSS, frontend frameworks, scene graphs. With 3D though, I would think most of the training data is imperative, because of libraries like Three.js and Python scripting for Blender.

For your first point though, I don't think raw vertex data necessarily needs to be the output, it could instead be based on shape primitives with raw points as an escape route, with an architecture similar to the one Quiver/StarVector uses for SVG generation. I think llama-mesh and mesh-gpt prove this semi-viable for 3D?

Even some of those smart 3D object ideas you mentioned could still work with declarative, where you build constraints and resolvers and such into the compiler instead of treating each design as a program.

In my own experimentation with 2D, I haven't actually seen a major gap between the outputs from the agent for imperative vs declarative but I'm curious if you've done any testing with declarative languages for 3D and whether you see a quality gap. It should in theory be much more token efficient?

moonuon DeepSeek-v4-flash-vision-exp

I've been working on an agentic graphic design tool, so vision is quite useful for having the model check its own work. I'm already seeing improvements with this model vs the text-only one.

moonuon DeepSeek-v4-flash-vision-exp

I imagine this is based on their 'Thinking with Visual Primitives' paper, and they had mentioned that the weights would be released for that

moonuon Best code editor without AI?

Zed is a good one, and it has a single toggle that lets you turn off all the AI features

moonuon All You Need to Know about JEPA

I like the demos on your landing page, quite fun. I don't think I've seen VLMs used in this kind of real-time context outside of robotics before. I feel like the actual ideas behind JEPA make a lot of sense for increasing sample efficiency and is probably a lot closer to how our own brains work (considering that people with aphantasia or those that lack an internal monologue still function just fine).

moonuon DeepSeek Harness developer preview

This has been a pretty big topic of discussion recently with Prime Intellect's new harness making leaps on ARC 3's public dataset. This is probably a bit overstated considering that a big focus of the benchmark is to test the model without custom harnesses, but you can imagine how for some tasks, especially long running ones, this kind of on-the-fly context management + tool generation could be quite useful. It gets better over time, it can build shorthand and tools for token efficiency, like a loose approximation of continual learning.

moonuon Muse Code and Muse Spark 1.2

Yeah, I have it enabled for just one of my projects, and it says "You're enrolled for complimentary daily tokens." Haven't been billed for any usage with this. Their tooltip doesn't mention the newer models, but it works for those too. I used them in a recent project that I knew wouldn't hit the rate limits. Not sure how eligibility is decided though.

moonuon Muse Code and Muse Spark 1.2

I've been surprised by the reception to this, as OpenAI, for a while now, has had free API usage when data sharing is enabled (https://help.openai.com/en/articles/10306912-sharing-feedbac...)

moonuon Claude Opus 5

I'm pretty sure that was a fake screenshot made as a joke, not an actual job posting

moonuon Police officer investigated for using AI to 'create evidence' in multiple cases

https://x.com/mitchcohen/status/1476951534160257026?s=20 The replies explain that it was a leaf obscuring the face

moonuon MiMo Code Is Now Released and Open-Source

I don't think that's true? AFAIK OpenCode started as a TUI and their GUI app is Tauri-based, so don't think it was forked from OpenCode. You might be thinking of Cursor

moonuon Artificial intelligence is not conscious – Ted Chiang

Yeah it's a good question, I've also been thinking about harnesses and all these tacked on things we've done to add persistent memory, what makes that different, I don't know the answer, I guess that still 'feels' different than what we have, but it's hard to articulate how. As for the memory into weights thing, I meant along the lines of the Google TITANS/MIRAS papers that were released I think late last year.

moonuon Artificial intelligence is not conscious – Ted Chiang

My favorite explanation for what consciousness is one I read in a Thousand Brains, I found it quite elegant. It posited that consciousness is a natural derivation of embodiment + memory + the ability to create reference frames (which the book lays forth as the fundamental basis by which our brains work). Essentially, the idea is that just as we create reference frames to understand the world around us, because of memory, we begin to develop one for ourselves as well. Because of this, without a more integrated memory (built into weights), it seems unlikely that LLMs might "gain" consciousness.

moonuon Thoughts and feelings around Claude Design

You should try the Arrow SVG model by Quiver, should be much better at that sort of thing since it's made for that.

moonuon Gemini Robotics-ER 1.6

Idk if you've seen this already but Taalas does this interesting thing where they embed the model directly onto the chip, this leads to super-fast speeds (https://chatjimmy.ai) but the model they're using is an old small Llama model so the quality is pretty bad. But they say that it can scale, so if that's really true that'd be pretty insane and unlock the inference you're talking about.

moonuon Ask HN: How do systems (or people) detect when a text is written by an LLM

Pangram is probably the best known example of a detector with low false positives, they have a research paper here: https://arxiv.org/pdf/2402.14873. They do have an API but not sure if you need to request access for it.

For humans I think it just comes down to interacting with LLMs enough to realize their quirks, but that's not really fool-proof.