Not really. Whether you agree with LeCun's assertion that "LLMs Are a Dead End" or not, world modeling is the same domain. "World Modeling" in this post is confusing because it seems to reference the deep, specific machine learning that goes into these frontier world models and self-driving cars, where it's really just vibe coding turned at the problem of modeling the sort of 3D worlds you'd find in a video game.
this is a one-shot result but i have a really really lengthy prompt: https://github.com/PhiloLabs/fable51-worlds/blob/main/union-... with clear guidance in using subagents and self-QA loop.
~2 hour (extensive subagents usage), total ~8M tokens, ~$33 under API
Did you need to iterate on the prompt, or did you have a model help you author it? I frequently have problems with orchestration instructions in-prompt, and your is huge. Maybe this is just better with Fable? I honestly haven’t used it much.
the topology/texturing critique is fair for mesh generation, but code-generated worlds mostly sidestep it. when the model writes three.js or blender scripts, geometry comes from primitives, csg, and parametric construction, so topology is clean by construction rather than something you clean up after. texturing is still a gap, agreed, though procedural materials cover more than people expect.
yes experimenting with it actually, will update here! in fact we've generated most of the tourist spots in sf, should be reflected in the repo soon too
yes we're working on it! trying to push a few open world rpg games with real economy and game design. it's also super interesting to benchmark the current models' capability in this direction, since this is a naturally hard and multimodal coding task
we're working on a survey paper about world modeling via code, with folks from frontier labs (qwen omni, oai, etc) and academic institutions (e.g., oxford, stanford, etc) reach out to us about collab: team@philolabs.ai
fable 5.1 generated an interactive 3D union square, and the agent filmed its own tour guide vid inside it. you can walk Powell to Stockton, read the actual storefronts, cross a working intersection, watch a cable car go by. went inside Apple and the Nintendo store, lower level included
excited to share opencanvas, a weekend project by ai engineers from mai, google, and anthropic that we're now open sourcing.
what it does:
transform any pdf document or topic into professional presentations in minutes using ai. the unique part: it has a built-in evaluation system that helps presentations self-evolve and improve.
key features:
- pdf to presentation conversion
- topic-based generation (just describe what you need)
- ai evaluation and self-evolution
- generates in minutes, not hours
- clean, professional designs
why we built this:
we were all tired of spending hours creating presentations from research papers and documents. most ai tools just generate basic slides - we wanted something that actually understands content and improves itself. turned into a fun weekend hackathon between colleagues.
