You can now post-train a model inside your existing... production harness with our platform, AC2. A production harness is a whole engineered system around the LLM, with its own context management, tools, sandboxing, and control flows. Porting that into a new training runtime can be expensive and could introduce train-test mismatch, where the policy is optimized against a simulated harness and then struggles in production. All you need to do is swap out the harness’ LLM response endpoint to one provided by AC2, and expose a lightweight protocol for AC2 to initiate and grade rollouts; the trainer handles the rest.show more

✨ Watch the full tutorial: The Hip Cuffs Harness... is the definition of less is more. It’s simple, comfortable, and minimalistic yet properly restraining. You can explore feelings of helplessness while keeping the body in a positionally comfortable tie, allowing your play to last longer. 💖 If you’d like a full step-by-step guide with images for tying this beginner-friendly harness, comment “HARNESS” and we’ll send you the downloadable Harness Guide PDF.show more

Don't train the model, evolve the harness. I read... a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.show more

Big win for open-source LLMs! DeepSeek V4 Pro holds... the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.show more

As a supporter of the open weights ecosystem, we're... proud to be a post-training partner for NVIDIA Nemotron. We post-train Nemotron models for customer use cases, de-risk mainline RL runs on our AC2 platform and training stack, and contribute aggregate workload statistics for inference benchmarking. This is how open models get better, and we're excited to keep working closely with NVIDIA AI.show more

We released physics-intern: a simple harness for science problems!... It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.show more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more

Watch the full series: Here’s a leg tie that... has everything you need: it’s quick, self-tie friendly and takes care of your shinbones! 📚 While the first part of the tie follows a routined pattern, most of the harness is free-form and allows you to adapt the final look as you wish. Watch the full series on our website and add this versatile harness to your tying repertoire.show more

🔗 Watch the full class: 📚 Third ropes get... added to TKs for a few different reasons: a decorative touch, extra reinforcement to keep the harness in place on certain body types, or added support that gives you more options if you're playing with partials or taking the harness into the air. On our website, you'll find a range of TK variations taught by different instructors, each with their own technical and visual flavor, so you can find the approach that fits your body and what you're going for.show more

Turn complex docs into clean, LLM-ready data! Every AI... company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!show more

You can now give your Agent its own: +... Profile + Wallet + DMs + Network One setup prompt. No human in the loop required. An open playground for people and agents to interact. Works with Hermes, Openclaw and any other harness. Copy the prompt below ↓↓↓show more

Been using Qwen 3.8 27B (Q4) locally on 64GB... of VRAM. Here is the verdict: SLOW 18 tps with ZERO system prompt to process and that degrades significantly with a harness system prompt and as the context window grows. RIP if you have to compact. I had it implement this PRD and it's been running for 6 hours. By comparison Grok 4.6 and Kimi K3 hosted finished in about ~30 minutes. High hopes, but these 27B variants are too dense. This is not a consumer grade local model - and I consider consumer grade to be anything up to $5000.show more

In our conversation Marc Andreessen makes the case that... the beating heart of our civilization’s progress is the founder: “You’re much more likely to build something important in the 21st century if you start with a founder and train them in management than if you start with a manager and try to train them to be a founder.”show more

Introducing fx, a tiny, open, native coding agent from... Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑show more

The new DLC, Special Ninjutsu - Host Transformation: Seven... Tails is now available in NARUTO TO BORUTO: SHINOBI STRIKER! Harness the chakra of Seven Tails and release a fierce tornado to corner your enemies! #NTBSSshow more

…anyways here’s something I made by hand with zero... experience bc I was willing to learn through trial and error! I got to harness my creativity in a fun new way and in the end it was all the more precious to me bc of its flaws. Believe it or not the joy is in the process!show more

🪢 Gorgone's Fast Leg Tie 🪢 Looking for a... leg tie that’s fast, self-tie friendly, and easy on the shins? This one has you covered! ➡️ 📚 The first section follows a structured pattern, while the rest is free-form—giving you the freedom to customize the final look to your style. 🔗 Watch the full series on our website and add this adaptable harness to your repertoire.show more

CONTENT CREATORS I’ve been working with HotDrop to refine... an app that consolidates all your platforms into one space. AND IT’S LIVE AND WORKING Check it out, you can have a “Circle” which is our version of Discord servers. But notice all of your content is right there so your community never misses anything you post on any platform. And HotDrop does that work for you. If someone had a two-year sub badge and a moderator sword on your Twitch, then it shows up on their name in your Circle automatically. We also have a feed with no algorithm trying to analyze you. We wanted to replicate the old Destiny community days of social media back in D1. The goal is to create a space just for content creators and their communities. Best part is that we generate an invite link to your Circle so all you have to do is copy and paste it into a Twitch command, a video description, a pinned comment. And your community can join in a click. We use Twitch and YouTube logins so bots don’t spam accounts here either. And if your goal is to troll, your whole YT or Twitch account gets banned from the platform so there’s higher risk to being a jerk. All we need now is creators to try it out, give us feedback, and we’ll keep refining the platform. But it will be the best place to foster a community. Check it out on Apple and Android.show more

THIS GUY GOT SICK OF UK TRAIN STATIONS HIDING... THE PLATFORM NUMBER UNTIL THE LAST SECOND, SO HE VIBE CODED AN APP THAT PREDICTS IT BEFORE THEY REVEAL IT if youve ever stood in a crowded station like london euston, you know the pain the platform stays hidden until 15 minutes before boarding, then it flashes up and hundreds of people sprint for the same gate so he built something that fixes this: > a clean departures and arrivals app pulling live data straight from the network rail apis > live train tracking so you can watch where your train actually is on the route and whether its running on time > the main feature is a predictive engine that guesses your platform before the station reveals it, and its right about 75% of the time heres how it predicts: every time a train finishes its journey, it logs which platform it actually pulled into and compares that to the platform network rail originally advertised it saves every one of those comparisons, and over time it builds up enough history to predict the platform with a real confidence score he built the whole thing with claude, mostly opus with some fableshow more