surreal_

yes we added the side by side comparison, check out the readme!

added the hand-painted style kyoto: https://github.com/PhiloLabs/fable51-worlds/tree/main/kyoto-...

ik, "world model" has too many definitions at this point. imo the bar is just: can it simulate the world.

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

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

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

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

check source code + more worlds soon

hey everyone,

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.

github: https://github.com/genmini-ai/opencanvas

would love your feedback and contributions. happy to answer questions about the implementation or how we collaborated across companies on this.

what features would you like to see next?

hi folks in ai/ml,

we built slidebee to solve a problem we all face: turning a dense paper into a decent presentation takes hours.

slidebee does it in minutes. you paste a url, we generate the slides.

see for yourself: reasoning in latent space: https://slidebee.genmini.ai/slides/20250910_054156/slides/pr...

rl for agents: https://slidebee.genmini.ai/slides/20250908_044442/slides/pr...

how it works: it's not just a text summarizer. our ai has multimodal understanding. it parses the whole paper—text, figures, tables, and equations—to build a coherent story.

our open source promise: we want to build this with the community. if this post gets 200 upvotes, we promise to open-source the entire project. this will tell us it's a tool worth maintaining and evolving together.

join now at: https://slidebee.genmini.ai/