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?
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.
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).
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.
I enabled all data sharing settings but still don’t have a message about free use on that screen - the help page says free tokens are available to “some” users - is that 1% of users, 40% of users, etc?
Does your screen have the message that you’re getting free tokens?
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.
I had no idea about this before. I just enabled it.
You're eligible for free daily usage on traffic shared with OpenAI.
Up to 250 thousand tokens per day across gpt-5.4, gpt-5.2, gpt-5.1, gpt-5.1-codex, gpt-5, gpt-5-codex, gpt-5-chat-latest, gpt-4.1, gpt-4o, o1, and o3
Up to 2.5 million tokens per day across gpt-5.4-mini, gpt-5.4-nano, gpt-5.1-codex-mini, gpt-5-mini, gpt-5-nano, gpt-4.1-mini, gpt-4.1-nano, gpt-4o-mini, o1-mini, o3-mini, o4-mini, and codex-mini-latest.
Usage beyond these limits, as well as usage for other models, will be billed at standard rates. Some limitations apply. Learn more.
I tried following this page, and it's certainly a lot more complex than what Meta is offering. Different price tiers, opt-in configurations, usage based availability.. I'll take the 10x discount for flipping a param switch over this all day long.
Seems pretty clear to me: enable it for the projects you want, and there’s a 1M / 10M token limit per day, depending on the model you use. Assuming an average context size of 100k tokens, that is 10 to 100 requests, which is not a lot. Reason enough to prefer actually paying for Meta as well.
1 million free tokens per day might sound like a lot. But that equates to something like 20 minutes of actual coding usage, because cached inputs are counted towards that limit. It's still great for running big singular requests, like solving some math problem with GPT 5.6 Sol Pro max reasoning effort.
Also, in a desktop browser at the page's [1] lower left it says "Personal organization", so if the 'organization' term is the concern, OpenAI still seems to use the term 'organization' even for personal accounts.
In my experience using DeepSeek v4 Flash free tier (context size limited to ~200k), the model isn't nearly as good as the paid one for agentic coding tasks. Unsure, if that's the case with these other providers too, though I wouldn't be surprised if it indeed is.
If you have the link for the page handy, I'd be curious to find the original revision on the wayback machine. That's too funny, especially if they've silently walked it back since.
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
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?