Introducing RL Environment Creator Skill Now any one can... create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.show more

This is hugeeee for open-source RL environments. You can... now discover environments across OpenEnv, Verifiers, Harbor, NeMo Gym, and more, all on the Hugging Face Hub. A common home for RL environments is long overdue. Excited for what’s coming next !show more

A Severance Vision Pro Environment was featured in a... WWDC25 developer session Don't expect it to make it to the Environment tab; it's just being used as a example for environments that sites can now provide via the web.show more

AI has had exactly two scaling axes that worked... so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inferenceshow more

Can “chicken” make a base model reason? 🐔 Yes!... Why? With the right first tokens, base models can match RL in reasoning. We trace this to learned training data associations and use a simple data edit to make “chicken” elicit reasoning too. blog:show more

🚨 New: Integrating Harbor (Harbor Framework) for end-to-end Computer-Use... evaluation(for Windows and Linux) at scale with Thinking Machines' Tinker, OSWorld, Daytona, and bare-metal servers. We just added support for Computer Use, Tinker, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇show more

Hi everyone! My class “A-Z of NPR 3D Environment... in Blender” is now up for pre-order on Coloso! (Coloso Global) I will guide you through the essential skills in Blender and show you how to create stylized environments! Link: #coloso #Blendershow more

The next big AI breakthrough might not come from... a bigger model. It might come from data no model has ever seen before. Most AI labs have already trained extensively on publicly available data. But private codebases, real-world tasks, and RL environments are still largely inaccessible. DataVendor is changing that. A marketplace where AI labs can discover, evaluate, and license private training data. This is a pretty interesting direction for AI infrastructure.show more

Did you know that GlobalEye can monitor air, land... and sea at the same time? By combining multiple sensors into a single platform, it creates a real-time view of the operational environment — even in complex or jamming environments. GlobalEye creates time to act.show more

The AgiBot X2 Ultra humanoid, only on Dimensional Full... SLAM, navigation, multi-camera perception, hosted teleoperation, RL training environments, and an agent-native control interface Developers on DimOS are shipping hundreds of humanoids into production today Get building 🦾show more

new skill: create-canvas. last week I made a skill... to put every component from a repo on one canvas. I started using it with my agent to create variations, compare ideas, and iterate visually without leaving the codebase. so I made a new skill around that workflow. instead of moving your work into another tool, bring the canvas into your codebase and use it to explore UI with your agent, using the real components, styles, and project context already there.show more

Today we announced Workshop – a solution for launching... sandboxed development environments in Ubuntu with a single command. Spend less time on configuring your environment: with just a few lines of YAML, you’ve got a reproducible environment you can use across machines. Find out how it works at:show more

we just released a new blog "Training a coding... agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:show more

Introducing autoresearch for arXiv papers: replicate and experiment on... any arXiv paper using an army of Claude/Codex agents For post-training, your agents can use Tinker to launch concurrent RL runs while you watch your experiment tree grow Try it out now on OpenResearch:show more

having a centralized skill repo in the company solves... a lot of otherwise annoying problems: - visibility on which skills are actually being used, in which use cases - duplication / needing to copy same skills into a repo - allows non-technicals to use and create - version control - eval the skills the common approach to this is to throw everything into a shared GitHub repo, butit creates a poor user experience and misses a lot of the observability benefitsshow more

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base... idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.show more

if you're making 2D pixel art games for #vibejam... this is solid. generate a sprite, create an end frame, prompt the animation between them worth checking. you can use with game creator skill design your game with placeholder wireframes using your agent, replace with final sprites latershow more

🚨Current scalable RL algos train a policy w/o value... func, which is limiting with learning in open-ended, non-stationary, dynamic environments. But, how to scale value-based RL with more data/compute is unclear... Not anymore: presenting scaling laws for value-based RL 🧵⬇️show more

Opposition in the batters box isn't just a layer... of complexity, an obstacle to overcome, it is the central feature that gives meaning to movement. My sense is that many in the baseball community view the live batter as a linear step to master after mastering other lower complexity pieces, instead of the central feature that we design our training environments around. Part of me understands why this is the case. Pitching is in a challenging place training wise because the behavior of pitches, movements, etc. change so much when you go low effort. In addition we have some limits on volume each day due to throwing being the single fastest movement in sports. Other sports can do unique warmups to work on interpersonal distance (football/basketball/soccer) and tagging games for more of a martial arts context. I simply can't have all 100 throws of a pitchers workload that day be to a live batter. And while I see value in pulling an athlete out of context at times to work on different things, ultimately, the entirety of my paradigm to train pitchers is how to do the real thing MORE, to keep them embedded in a representative environment, rather than treating it as the final step in a linear progression.show more

Excited to announce AI Research Skills - an open-source... library of 82 specialized skills for AI coding tools. One command gives your agent expert knowledge in: → Model training & fine-tuning (TRL, Unsloth ...) → Distributed systems (DeepSpeed, FSDP ...) → Inference optimization (vLLM, TensorRT ...) → Agent building ? (Langchain, AutoGPT ...) Works with Claude Code, Cursor, Gemini CLI, Windsurf, and Codex with one click interactive installation @ npx orchestra-research/ai-research-skills If you found the ML paper writing skill useful, check out the comprehensive collectionshow more

GPT-6 Astra test 4/n Prompt: "Implement pen spinning with... a dexterous hand. Use Isaac Lab for RL training, use the Sharpa hand, and create the pen mesh yourself. Give me a trained RL policy and a visualization video. You are free to search the web and download papers or anything else you need." After running autonomously for a day and a half (including training the policy), this is what we got: Credit: my student Chengyang Lishow more