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

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

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

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

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

RL is painfully slow 😭 — bottlenecked by super-long... CoT rollout. 🔭 Sparse attention should help, but naive sparse rollout hits a brutal efficiency–stability tradeoff: A tedious trial-and-error sparsity sweep for each dense policy is required before an actual RL run. 🐤Sparrow chirps no more pain! Introduce Sparrow: Sparse Rollout for stable and efficient long-context RL. Sparrow finds that: 💡As long as we keep the tail distribution mismatch throughout the sparse rollout above a critical threshold, the RL training will be stable. 💡Even cooler! Through comprehensive control studies of Qwen3-1.7B, 4B, 8B thinking models RL with 40K rollout max length, the critical threshold stays constant across model sizes. 💡Sparrow then finds the optimal dynamic sparse schedule to reach the threshold with minimal cost. 💡Sparrow's findings are empirically validated to generalize in Qwen3-14B, and hold on both Math and Coding RL. 🐤Sparrow empirically helps achieve 2.2× / 2.4× / 2.0× rollout speedup on Qwen3 1.7B / 4B / 8B thinking models, while keeping training stability over extended RL steps. We release the 🐤bird in the following formats. [1/n] Paper: Code: Blog:show more

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.show more

We are entering an extremely exciting era for open-weight... models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.show more

Claude Code can now go find the right skill... itself, instead of you searching for one. it's called find-skills. a small package that plugs into Claude Code, and instead of you hunting for rest, you just describe the task and it searches the whole open skills ecosystem, finds the ones that fit, and installs them for you. > tell it what you're trying to do, in plain english > it scans the skills registry and maps your task to real skills > it pulls the right ones in and sets them up half the time you don't even know a skill exists for what you're doing. now you don't have to.show more

TESLA HALTED MODEL S AND MODEL X PRODUCTION TO... BUILD AN ARMY OF OPTIMUS ROBOTS The Fremont assembly line was torn down in 46 days. In its place, Tesla is building a line for humanoid production, aiming for a million units a year A humanoid robot is a body shaped like a human. Physical AI is the intelligence that controls that body Walking and making coffee is often just imitation learning from a scripted routine. But once the environment shifts, the learned trick stops working Language models had the entire internet to train on. Robotics has nothing close to that scale of data, which is why one giant brain hasn't worked for anyone yet The industry is moving toward modularity instead - separate models for vision, movement, and planning, each improved on its own The real question is no longer whether a robot can move impressively. It's whether it can pull its sensors into one picture of the world and adapt to whatever wasn't scripted for itshow more

MiniMax H3 is now on Magnific and honestly, there’s... a lot you can do with it. You can mix text, images, videos and audio in a single prompt up to 9 images, 3 videos and 3 audio references. Start creating now: It can generate up to 15s of 2K video with synced sound, including voice, music and effects. And you can go beyond generation too: edit clips, remove objects, transfer motion, and control the camera, character and voice. But the multi-reference workflow is probably my favorite. Give it your product, character, environment and motion references, and H3 pulls everything together. It feels like a much easier way to go from an idea to an actual finished video.show more

GPT-5.5 by Reasoning Effort: I've asked it in Codex... to create a physics-based visualisation of RL cycles for different sized models (70b, 1t, 10t), to demonstrate how the amount of RL you can do differs by model size. My assessment of each: - Low: weird slop - Medium: kinda cooked - High: sort of tried but ultimately incoherent - Extra High: elite - really nice idea and well executed Obviously this is just one shot, but worth trying different reasoning levels for the new models, medium seems to be pretty good for GPT-5.5 and it was really bad for many previous GPT models.show more

NEW HTML VIDEO SKILL: Claude can now make photo-grid... promo video ads like these. These are very popular offer-style ads that work well for bottom-of-funnel conversions. Brands will often run these when they're doing seasonal sales, for example. It's pure HTML, so it's very cheap to make because there's no video generation cost. You can create dozens of variants very fast and then test them in Meta. All you have to do is install the skills and give Claude your brand website. This skill is insane - it'll make the entire Ad and give you a link where you can download the mp4 file. > If you want more variants, just mention in the prompt > If you have a specific concept in mind, just mention in the prompt > If you want any edits on the generated ad, just mention in the prompt Comment Goose and I'll DM you the skill (must be following so I can DM you)show more

Alright, now that we know *what* an agent is,... how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.show more

Figure is aiming to develop the world’s largest and... most diverse real-world humanoid pretraining dataset. For this purpose, they’re partnering with Brookfield, a global asset manager overseeing $1 trillion in assets, including 100,000 residential units, 500M square feet of commercial office space, and 160M square feet of logistics space. The data collected from this collaboration will be used to train Figure’s Helix AI model, enabling humanoids to perform tasks autonomously in real-world environments designed for humans. In addition to data collection, the partnership will explore support for next-generation GPU data centers, real estate for robotic training environments, and commercial use cases across Brookfield’s global footprint.show more

In the past week, I was able to build... the following games: - An endless runner - A tower defense - A Mario Party-like mini-game - An arena-based shooter The key unlock here was the ThreeJS skill With Opus 4.5 & GPT 5.2 - Claude Code / Codex CLI have much better end results now. With each game, I continued to update the skill based on bugs and issues faced - so it progressively got better and better at building the gameplay I was looking for. I've been doing this for a while now - and I can say that the leap in building games with vibe coding is real.show more

OpenAI's Deep Research is getting a run for its... money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!show more

Tried something new today. I made a character based... environment and color direction board. First extracting the character’s palette, then translating it into an environment palette, and finally mapping where those colors should appear on the background, midground, foreground, lighting, shadows, and accents. Hard to tell if it’s fully working in this clip, and this might not be the best example, so I’ll test it again with a different style and a longer video, perhaps. This is just me overcomplicating things, 100% not needed. You can get same results with simple prompts and random environments. Prompts below.show more

more frontend vibecoding tips (results below): WHY YOUR VIBECODED... FRONTENDS ALL LOOK THE SAME AND SUCK: when asked to make a frontend, the agent/llm will default to the center/average of its training data (in a very loose sense). through the training process, the model essentially converges on some default UI style. it's very capable of doing things that are different from this style, but you have to ask! for instance, ChatGPT tends to reply in the same tone for all users untill you interact with it and instruct it differently ("be sassy", "eli5"). the second reason is that most of us are not good at coming up with designs and describing them precisely (see my tweet on a crash course in common components, which i'll link below). treat frontend generation just like any other eng task! you need to provide a good detailed spec. TIPS: 1. give ur agent screenshots of designs you like (you may not know the right words to describe them but the agent will! a pic = 1000 words) where to find ui inspo? Behance, Dribbble, Mobbin (Mobbin is paid but worth it!) 2. ask ur agent for proposals, this helps "seed" different directions so the final frontend stands out. don't be afraid to go back and forth. 3. ban certain tendencies: no Inter/Roboto, no shadcn (controversial), no gradients, no emojis 4. encourage the agent to be extreme and make bold decisions, not safe ones. i think that the underlying models tend to get taught during RL/fine-tuning to make conservative choices that produce reasonable but boring frontends 5. give ur agent Figma MCP. the best results will come if you mockup your vision in Figma first. 6. Ideally choose an agent with vision capabilities TLDR: Most people are tremendously underusing agents for frontend design. They are much better than you might expect.show more

Sharing my new skill! It keeps track of high-signal... X accounts for top AI news, papers, projects, etc. Total gamechanger for me. Built with X MCP tools. Give your agent the skill and tell it to generate the artifact with top stories. Works for Codex, Claude, Hermes, OpenClaw, or whatever you use. 3 steps: 1. Set up X MCP - X API: 2. Install skill here: 3. Run prompt: "Use the x-agent-intelligence skill to build a self-contained local feed from my X MCP connection; ask for my source handles if needed, save feed.html, and validate it." It should generate a nice, beautiful HTML artifact like the one shown in the clip. You can tune it however you want. You can then set a schedule/automation to do this daily or whatever cadence you prefer. I have it every 4 hours. You will need to curate the X accounts yourself, but I have shared a few good ones under the assets. You can ask your agent to tune it to however you like. I have also shared my personal feed with our community here: I understand if it gets tricky to set up. Please reach out to me in the community forum. I plan to do a little tutorial or live session soon to help others reproduce the process. You can also store the feed as a wiki, as I have in my own implementation, but that's optional. If you encounter any issues or have ideas on how to improve it, please open a PR.show more

IF YOU SEE THIS POST, IT MEANS I'M LOOKING... FOR A GAME PROJECT TO JOIN Hi, I'm Nera, an art director leading a small game art team. We've recently finished our latest game project, and we're now looking for a new game to work on. Our team can help with the full art production of your game from characters, environments, objects, and animations to UI. We can also help shape the visual direction of your game from the ground up. You don't need to be an experienced developer or have a large team to make a game. If you have an idea you're passionate about, we'd love to hear about it. If you're working on a game and looking for an art team, feel free to DM me. 🥰🩷show more