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

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

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

Okay... this is actually insane. OpenCodex feels like the... open-source breakthrough I've been waiting for. The best part : You can plug multiple providers into the same OpenAI Codex harness and switch between models depending on the task. Running low on tokens? No problem. Use another provider. OpenRouter free model today? Plug it in. This completely changes how I think about AI coding workflows. And yes... it even works on mobile. OpenCodex might be one of the most useful open-source AI projects I've seen this year. OpenAI built an incredible harness. The open-source community just made it universal.show more

Okay this is kinda wild 👀 NVIDIA is basically... handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.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

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T... RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.show more

Stanford researchers did it again. They just built the... agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.show more

Black Forest Labs just announced FLUX 3: a unified... multimodal model for image, video, audio and action prediction. Founded in Freiburg, Germany, one of the few globally significant European companies in the AI ​​sector. The current release is gated early access, not open source. But if FLUX 3 Dev actually ships with usable open weights, this could become one of the most important open-model releases in generative video yet. Especially after the Chinese Minimax H3 release. BFL claims, based on preliminary internal comparisons, that FLUX 3 outperformed models such as Runway Gen-4.5, Luma Ray 3.2, Kling 3 Pro, and Seedance 2.0. However, these figures stem from the early-access phase and do not constitute independent validation. Be that as it may, it's great to see the quality that today's video models can produce at affordable prices. Something that would have been unthinkable a year ago. Really cool release!show more

you can run claude code inside antigravity completely Free... with zero credit card and no rate limits 😳 use openrouter’s free models + antigravity. no anthropic bill. no paid api keys. takes 10 minutes to set up. what you get during this setup: - full claude code agent experience - strong coding models (including deepseek-r1, qwen2.5-coder, llama-4, grok-4 free tier) - antigravity’s clean workspace and sandbox - unlimited usage (as long as you stay on free models) - easy model swapping - zero cost full setup guide (100% free): step 1: install antigravity -go to and install it -create a new workspace step 2: install claude code - inside antigravity, install the claude code extension from the marketplace - open the built-in terminal step 3: create openrouter free account -go to - sign up with google (no card needed) - go to keys and create a new api key step 4: set the environment variables -in antigravity terminal run: export ANTHROPIC_API_KEY=sk-or-xxx export OPENROUTER_API_KEY=sk-or-xxx step 5: launch claude code with free model -run this command: claude-code --model deepseek/deepseek-r1:free or try: qwen/qwen2.5-coder:free if you already have antigravity? skip straight to step 2. after 10 minutes you’ll have a full agentic coding setup running for free. this is currently one of the cheapest ways to run serious coding agents in 2026. bookmark this before they limit the free models.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

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

Codex can run Qwen-3.8-max now as well!! Alibaba most... capable model, dropped today and it's already in my codex picker. It's a token plan subscription, not metered api billing. You take the key from your Qwen plan, drop it into Codex Router, and it spends down the plan instead of your card. There's a catch though. Qwen's official setup switches your whole codex over to them, so your ChatGPT models stop showing up at all. That's exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, Grok, kimi, Deepseek and now Qwen 3.8 max all sit in the same picker and it can grab whichever one suits the job. Router's open source, setup's in the video 👇show more

I explored a further possibility with local models: Qwen3.6... 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.show more

if you use Codex and you're stuck on GPT... models only, this fixes that. it's called codex-router, open source. drops other models straight into your normal Codex picker, right next to the GPT ones you already have. what it adds: - Grok, Kimi, Deepseek, Claude, all in the same picker - oauth login per provider, no api key needed - your GPT models and Chatgpt login stay untouched setup: point Codex at the repo, let it read the readme, it installs itself one snag: if you've got the Chatgpt app and a separate Codex on your path, you can end up running two different Codex versions, and the older one can choke on newer config it doesn't recognize. if the install looks off after, that's probably why, reinstall clean.show more

50% cheaper Claude inference with just one line of... code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.show more

this is the best trick to maximum usage limits... on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)show more

Codex can now run Deepseek-v4- flash! There's a catch... though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇show more

DeepSeek R1 is *the* best model available right now.... It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.show more

90% of "AI developers" just download pre packaged GGUF... files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.show more