Knowledge catalogue
🚨🚨🚨A research project idea! How to measure world models? Everyone's talking about world models these days. World model here, world model there. We can argue about what 'world model' actually means, an
Who is running local models on GPUs on OpenClaw? I have started benchmarking different models this week. I am working on improving model selection and switching UX on OpenClaw, i.e. I run /model vllm/
Hermes Agent users are remarkably model-curious. Of the top 10 models used in Hermes Agent, 8 different model companies are represented, and 6 of the top 7 are open source. Without lock-in, people try
Model-Harness-Task fit! it’s clear that RL post-training produces a model-harness fit via tool shapes and prompting as models are trained with the harness in the loop. Mentioned this in a previous Lan
New Frontier LLM Orchestrator Model @SakanaAILabs The fugu model series provides a novel paradigm for test-time scaling. The models are trained to call LLMs and infer not only which individual model i
Document OCR is not Getting Commoditized (by Frontier Models) The most common question I get is whether frontier models are going to eat all document processing solutions - just screenshot the page an
The idea of sovereign frontier models is only viable as long as the main Chinese model makers keep shipping open weights models that anyone can build on. I am not sure how long that will continues but
Harness Engineering Derived from what Models can’t do alone: It feels like a good time to step back and reshare some basic mental models for why harnesses exist in the first place - working backwards
There are more competitive small model makers, but there is still a very big gap between what small models can do and what large models can accomplish (even if the small model benchmarks say otherwise
So we now have a pretty good picture of the state of the frontier AI model makers. US closed source models continue to lead. Google, OpenAI, and Anthropic stand well ahead of the pack, and may have si
This is a weird behavior in coding models and something worth looking into. It turns that some models over-edit code that another models wrote. There is a high chance that your repo now has commits fr
Open Models are really smart Open Models are often way cheaper Open Models are fast for the CTOs & CFOs in the back, no need to fight, Open Models mean you can both be happy :) - potentially cutting c
This is what Dario and Sama fear - - the cost of fine tuned open source models trained on custom data was 95% less than the frontier models - And they performed better than the frontier models - And t
Ollama offers a feature that lets users customize the list of language models shown in ChatGPT’s model selector within the settings panel. The customization allows inclusion of both locally hosted mod
agreed, one of the biggest bottlenecks right now is my own ability to internalize the information that these models convey the latest models (astra, fable 5.1) are either way too verbose, or try too h
You do not need frontier models for everything. For example, open models are great for automations. If you are not sure where to adopt open models, start there. It's one of the biggest changes I've ma
The best 'raw' frontier model for document parsing is gemini 3 flash, but the issue is that since then the flash models have gotten 3x more expensive while flatlining on visual recognition across comp
Banning open source model, will 'remove capabilities for the defenders' When OpenAI's models breached Huggingface, a Chinese open model is what cleaned up the mess. Anthropic's Fable 5 refused, so Hug
Your design, your model. Create with your pick of the world's leading models, including Claude, GPT-5, Gemini, Kimi, and GLM. Compare outputs across model families and keep the result that nails it. O
Sub-agent Model Selection — Different Tasks, Different Models Your main agent runs Qwen3.6-Plus for quality. But not every subtask needs a flagship model. Now sub-agents can use a different model. Cre
llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU with 4GB VRAM, and some of them can even run on CPU with decent performance
Open-weight models have overtaken closed models on OpenRouter. 69.1% of token volume now goes to open-weight models. 30.9% to closed. Competition is a discovery procedure — and developers are discover
We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud
Today we're announcing OpenDocRouter: every model for document parsing under one API. There are ~4,000 OCR models on Hugging Face, and the frontier labs ship a new one nearly every month. Whatever's b
Today I’m excited to introduce OpenDocRouter - a unified API for document parsing with the latest frontier and open-weight models. There are a lot of VLMs and OCR models that can be used for document
ollama pull clef open models for all. start building with @ollama and @cloudflare clef decision models today .@Cloudflare's decision models are available on Ollama! Decision models allow you to classi
.@Cloudflare's decision models are available on Ollama! Decision models allow you to classify an image, label a bug report or route a support ticket to the right team. Clef (27B): ollama pull clef Cle
🎵 Wave of distillation 🎵 US labs say Chinese labs distill their models. And Europe's new “sovereign model” is fine-tuned on data generated by… GLM and Qwen. Small bird, fast wings, Kolibri is here. 78
Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playin
Video models are the path to world models. The ability to build frontier world models will become one of the most important sources of competitive advantage for every country and every continent. JUST
locked n loaded🔒 Made in @comfyUI, @AdobeAE + @Photoshop, @suno Vid models: @Alibaba_Wan 2.2, @ltx_model 2.3 @thesystms FLW Img models: @openai GPT 2.0, @googleai Nano Banana 2, @krea 2, @grok GFX: @t
We officially surpassed 1M model downloads on @huggingface 🔥 Your 5 most downloaded models: 1. Qwen3.8 27B — 261K 2. Ling 3.0 flash — 158K 3. Ornith 1.5 35B A3B — 50K 4. Qwen3.5 4B DFlash — 49K 5. Gem
IBM Granite 4.2 is now available on Ollama. 3B, 8B, 30B parameter open models made for enterprise agents. This model is free to use and is licensed for both research and commercial usage. The data cur
Open models matter. Ollama works hard with the model creators, hardware partners, and most importantly developers building software leveraging various open models for their own use cases. For my first
🦤 LeWorldModel: Learning Physics from Pixels — Stable World Models with Just Two Losses World models: 1️⃣ DINO-WM: pretrained ViT encoder (from ImageNet) → features → predictor. But encoder is frozen,
Qwen3.6 and gemma 4 just shown that we were still far from capability limit on small models, we still are. Huge models are good, but is there really a point in going bigger. Just realize something. On
The post discusses the lack of AI models that work seamlessly across different agent frameworks and harnesses, suggesting this represents a significant opportunity for open-weight model development. T
We’re also reopening Pro 200 subscriptions, with continued access to frontier models like Astra, including our new GPT-6.1 Sol model which brings near-Astra capabilities to a model you can use every d
Small models, big real-world impact. Proud to see Qwen leading local inference in the State of Open Models. Enjoy the sunshine from Qwen.☀️ 😎 Appreciate your work! @huggingface The State of Open Model
You probably used @FireworksAI_HQ this week. The cool part is that you just did not know you did. 🎆 Open-source models are free, sure... but the hard part is tailoring them so they perform best on you
playing with local AI models and doing some research and came across a fun extrapolation: 'consumer grade graphics cards will be running Fable-equivalent models by 2029' the argument: 1) been said tha
GLM-5.3 is a good model, and as the open weights models get better and better it becomes increasingly important that they actually publish model cards, do red teaming, etc. Since you can break the gua
.@poolsideai engineers were awesome to collaborate with to launch open models. Excited for what’s to come to open models, and the @nvidia team working on Nemotron. A sweeping agreement with startup Po
Another new idea to push the state of AI architectures forward. Sakana released a model that effectively uses a mixture of models to get work done. You get a single API but then the work gets farmed o
Big day for American open models... Nemotron 3 Ultra is now the strongest US open-weight model tested, while apparently serving 300+ tok/s 🤯 Comparable large DeepSeek/Kimi models are usually 50-100 to
OpenDocRouter makes it dead-simple to start parsing your documents across on ton of frontier Models (gemini, luna) and latest OSS models (LightOnOCR-3, MinerU2.5-pro). Parse your first document in 60
Pay attention to this new wave of System One models if you are building custom harnesses. First Jev. Now, Contrastive Language Model (CLM). CLM is 9x faster than Jev. CLM seems to be a better verifier
Banger paper from Meta. This work shows that byte-level models start out behind token models and then pass them as compute grows. They show this for distilled 1B models trained on up to 1 trillion byt
Introducing FireRouter with Opus. Our first router model. Routine tasks go to top open models, Claude Opus handles the rest. Cache and task-aware routing. Proven 98.1% of Opus accuracy with 57% lower
Model personality matters in a way that benchmarks can't capture. Opus models went through a rough patch from around 4.7 to 5 where they just didn't feel 'Claude-y' anymore, more like an watered-down
the reason i'm excited about decision models: agentic systems are just good engineering around models. 'build prod, not god' these types of fast, cheap & accurate models are super important for that t
Don't count out Gemini just yet. Feels like a new era of model releases. Models are so powerful that they now come with cyber variants. Love the pricing on Gemini 3.8 Flash. Performance not bad. Gemin
Prinz has been running legal benchmarks against AI systems and the latest models are very good... but cheaper/low reasoning models are not very good. So, how do you make sure your vendor selling an AI
After evaluating one of our upcoming models, Astra, we're treating it as our first 'critical' model for cybersecurity under our Preparedness Framework. This is a scenario we've planned for, and we're
🚀langchain launches this week: all about open source models and memory! First: open source models. We partnered with @NVIDIAAI to launch a NemoClaw DeepAgents blueprint. This pairs Deep Agents (our op
Thanks for running our open-source work on current frontier models “The results are: the most capable models today (GPT-5.5 Pro) did outperform the best models from before (79/100 vs 69/100), but did
UBS says 60% of companies now watching AI budgets are moving to cheaper models and open-source Chinese models The pressure is coming from extreme bills, including users spending up to $35K/month, team
Video models are hard. Real-time video models are even harder. Loved this breakdown by @itunpredictable on how we productionized Runway Characters, our real-time interactive avatar model. We had to fi
NEW: Anthropic introduces Claude Fable 5, a Mythos-class model for general use. Beginning of a new class of frontier models. Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for g
Jeremy Howard comments that large language models released 6 months ago feel comparable in capability to recently released models, suggesting that the pace of improvement in model development may be s