RO2⚡️

@danielhanchen @UnslothAI Got it, thanks! great product btw

@risingodegua @UnslothAI Oh yes so if there's no GPU or your system is not supported, only inference works for now

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

Turned my blog articles into one big design engineering skill that you can use with coding agents like Claude Code or Codex. It covers animations, component design, principles from my open source projects like Sonner, and more. emilkowal.ski/skill

"One poor bastard" GPT 5.4 is funny 🤣

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency of the model. 2) extracting explicit representations avoids continuously running a heavy generator, thus saves compute and facilitates real-time interaction.

I trained a neural network to mimic a forest trail near my apartment (web demo in the post) madebyoll.in/posts/world_em…

@juliarturc Recording

@risingodegua In what way is it broken? Do you mind sharing a screenshot?

Diffusion models clicked for me when I started seeing them through the lens of particle motion. I built this interactive playground where you too can clickety-clack to understand how drift, noise, and other hyperparams control diffusion. I hereby submit this as penance for the sin of YouTube edu-tainment 😇 Link in the first comment.

How far can you push diffusion training in 24 hours and $1500? We ran a diffusion speedrun in the next post of our PRX series. 32× H200 1 day of training The result is a surprisingly capable text-to-image model. Full recipe and code open sourced 🧵

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at @SpAItial_AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.

Come join us!

I spent all of Christmas reverse engineering Claude Chrome so it would work with remote browsers. Here's how Anthropic taught Claude how to browse the web (1/7)

yes things are changing fast, but also I see companies (even faang) way behind the frontier for no reason. you are guaranteed to lose if you fall behind. the no unforced-errors ai leader playbook: For your team: - use coding agents. give all engineers their pick of harnesses, models, background agents: Claude code, Cursor, Devin, with closed/open models. Hearing Meta engineers are forced to use Llama 4. Opus 4.5 is the baseline now. - give your agents tools to ALL dev tooling: Linear, GitHub, Datadog, Sentry, any Internal tooling. If agents are being held back because of lack of context that’s your fault. - invest in your codebase specific agent docs. stop saying “doesn’t do X well”. If that’s an issue, try better prompting, agents.md, linting, and code rules. Tell it how you want things. Every manual edit you make is an opportunity for agent.md improvement - invest in robust background agent infra - get a full development stack working on VM/sandboxes. yes it’s hard to set up but it will be worth it, your engineers can run multiple in parallel. Code review will be the bottleneck soon. - figure out security issues. stop being risk averse and do what is needed to unblock access to tools. in your product: - always use the latest generation models in your features (move things off of last gen models asap, unless robust evals indicate otherwise). Requires changes every 1-2 weeks - eg: GitHub copilot mobile still offers code review with gpt 4.1 and Sonnet 3.5 @jaredpalmer. You are leaving money on the table by being on Sonnet 4, or gpt 4o - Use embedding semantic search instead of fuzzy search. Any general embedding model will do better than Levenshtein / fuzzy heuristics. - leave no form unfilled. use structured outputs and whatever context you have on the user to do a best-effort pre-fill - allow unstructured inputs on all product surfaces - must accept freeform text and documents. Forms are dead. - custom finetuning is dead. Stop wasting time on it. Frontier is moving too fast to invest 8 weeks into finetuning. Costs are dropping too quickly for price to matter. Better prompting will take you very far and this will only become more true as instruction following improves - build evals to make quick model-upgrade decisions. they don’t need to be perfect but at least need to allow you to compare models relative to each other. most decisions become clear on a Pareto cost vs benchmark perf plot - encourage all engineers to build with ai: build primitives to call models from all code bases / models: structured output, semantic similarity endpoints, sandbox code execution. etc What else am I missing?

Performance Hints Over the years, my colleague Sanjay Ghemawat and I have done a fair bit of diving into performance tuning of various pieces of code. We wrote an internal Performance Hints document a couple of years ago as a way of identifying some general principles and we've recently published a version of it externally. We'd love any feedback you might have! Read the full doc at: abseil.io/fast/hints.html

Releasing Echo today is incredibly exciting for me — because it is a critical step for generative AI, enabling the creation of virtual worlds. Echo is our first world model at SpAItial AI. It turns text or images into explorable 3D environments — spaces you can move through, inspect, and build on. Seeing this work in real time still feels a bit surreal. My fascination with this goes back a long way: video games, virtual environments, and the idea of capturing the real world in 3D. As a researcher, I spent years working on 3D reconstruction, neural rendering, and scene understanding — all driven by the same question: how do we teach machines to understand the world? One thing became clear over time: the biggest bottleneck isn’t compute or rendering — it’s 3D worlds themselves. High-quality, consistent environments are expensive to create by hand and don’t scale to the experiences we want to build. In particular, I believe that the ability to generate virtual worlds is ultimately key towards understanding the real world. That’s why we founded SpAItial AI. We’re building spatial world models that combine geometric understanding with creative generation — models that can generate, edit, and eventually reason about 3D environments. Echo is just the beginning. For me, this feels like the moment when decades of research finally meet the imagination that got many of us into graphics, games, 3D understanding in the first place.🌍 spaitial.ai

🚀 Congrats on the release! can't wait to try this out.

Everyone and their mother has something to say about space compute. But no one has comprehensively broken down the physics, energy, cooling, economics, and the real work involved. So I built a 1st principles model to show you guys myself. astrocompute.dev

Introducing shadcn/create – Build your own shadcn/ui Customize Everything. Pick your component library, icons, base color, theme, fonts and build something that doesn’t look like everything else. Now available for Next.js, Vite, TanStack Start and v0.

If you've ever seen someone tweet some cool shader and thought "I don't really even know what a shader is and at this point I'm too afraid to ask" - I've written something just for you. makingsoftware.com/chapters/shade…