Search: “models”

The Sensorimotor World Model (https://arxiv.org/abs/2606.20104): a deep dive into the role of inverse dynamics modeling as an anti-collapse regularization for JEPAs. IDM is weaker than SIGReg as it do

Kog open-sourced on @huggingface the 2B model that they used to show a model running at 3,000+ tokens per second. Very cool work! https://huggingface.co/blog/kogai/kog-laneformer-2b-the-latency-first-

Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API. Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability w

🚨 Fable 5 is something to pay attention to. This is another 'I had early access to the new Mythos-class Anthropic model and I want to tell you what I thought of it' post. I know, I know, it's annoying

The Top AI Papers of the Week (May 18 - 24): - AIRA - MetaCogAgent - Memory as a Model - Code as Agent Harness - Weak-Model Critic-Comparator - OpenAI Disproves the Unit Distance Conjecture - Producti

Introducing Starchild-1 from @odysseyml, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear.

The UK AISI found Mythos Preview is the first model to solve both their cyber ranges end-to-end. No model had ever solved the AISI’s “Cooling Tower” cyber range before. We're getting it to defenders a

Jensen Huang describes his early collaboration with Elon Musk, noting that he provided computational support for Tesla's Model S and Model 3 vehicles through NVIDIA technology. Huang credits this prof

switching model providers is easy switching harnesses is less so model providers want to lock you in via harness we need open harnesses! TBH I don't agree with your take. I don't think Athropic's desi

This is an incredibly cool experiment It is also fascinating that the model knows information up to 1931, but, at least in some science topics, seems very stuck in the early 1900s. For example, it def

⚡ Meet Qwen3.6-35B-A3B：Now Open-Source！🚀🚀 A sparse MoE model, 35B total params, 3B active. Apache 2.0 license. 🔥 Agentic coding on par with models 10x its active size 📷 Strong multimodal perception an

Given the messy naming scheme used by all the AI companies, I caused a chart to be made showing the gain in GPQA per 0.1 version in model names (estimated, since model names skip version numbers). The

I was unable to retrieve the specific tweet content from that URL, as the post requires a logged-in X (Twitter) session to access, and search results did not surface the full text of that specific ...

if you want claude's managed agents w/o model provider lock in, this is the path! `deepagents deploy` lets you deploy an agent built on our model agnostic, open source harness in minutes you can easil

NVIDIA Nemotron 3.5 Super VL is now available on Ollama This model combines reasoning and visual understanding across a range of agent workflows. On a single GPU, this model delivers up to 5x higher t

CancerBench: the frontier model cancer cure benchmark. AI lab CEOs keep talking about curing cancer, so I made a benchmark. One metric: how many types of cancer has your model cured? All models are cu

New model for AMD Strix Halo users: My 198B Step 3.7 Flash release was a big hit, but this one may be even better: 298B-parameter Hy3, now running on a new 2-bit FPX codebook designed to map efficient

FULL INTERVIEW: Engineers Edward Coristine (@as400495) and Tai Groot (@taigrr) just released an ML model called Rampart for the National Design Studio. It's a local-first, open-source AI privacy model

This post announces an 8-9 billion parameter language model optimized for efficiency and speed, trained on a very large token dataset, and positioned as accessible for users with limited GPU resources

Today we're announcing ESMFold2, an open scientific engine to power prediction, design, and discovery across protein biology. The new model delivers state of the art performance on protein interaction

Tesla's Model S, designed by Chief Designer Franz von Holzhausen, marked a significant milestone spanning from its first customer deliveries in 2012 to its final production run in 2026, representing 1

The Harness is a Context Manager on Behalf of the Model What happens when the context window fills up and who decides? This decision is external to the model - The Harness designer must have some opin

Ethan Mollick comments on an impressive AI model achievement, noting that the performance gap between models appears consistent with historical trends based on his assessment.

dear god lol - new kimi model is a fucking beast. GPT 5.4 level coding, 76% cheaper than opus 4.7 and 100% open source / free to use, i mean look at this: > kimi k2.6 can code continuously for 12 hour

Last week, Anthropic announced Project Glasswing alongside Claude Mythos Preview, a model they described as so powerful at finding vulnerabilities they couldn't release it. The announcement featured A

Open everything 🔥 Open Harness, Model Choice, Open Memory (take it wherever you need), Open Protocols basically we’re in the middle of a model war, they all make great models but the optimal arrangeme

Amazon released the Nova 2 model family on December 2, 2025 at AWS re:Invent, comprising Nova 2 Lite, Nova 2 Pro (Preview), Nova 2 Omni, and Nova 2 Sonic, all featuring a 1-million-token context wi...

Interesting safety paper from Microsoft. They find that a weaker, unaligned model can split a harmful task into harmless-looking subquestions, ask an aligned frontier model each one in a separate sess

I am pleased to see that OpenAI’s new model is roughly on par with Gemini Flash and Opus 4.8 on prompt injection risk. Nice work! Evaluating and naming other labs turns out to be a great way to encour

Fable 5.1 is our best model yet for coding, data analysis, computer use, design, presentations, Tag, and the hardest long-running agentic work. This model is a pleasure to work with, and I've been usi

Qwen’s new Qwen‑3.8‑27B model has become the top‑trending model on Hugging Face. The release announcement thanks the community for its support and invites users to try the model and provide feedback.

The Qwen Team has released its flagship model, Qwen3.8‑2.4T‑A95B, on the Together AI platform (togethercompute) as of August 12 2026. This 2.4‑trillion‑parameter model is engineered for coding tasks a

DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's cloud. This model combines speed, efficiency, and frontier-level performance. Fast: 120+ output tps

The July 4th weekend All-In @theallinpod turned into a long argument about who owns the intelligence layer. The besties think enterprises just woke up to a trap they had been walking into, here's how

Something about this year’s @aiDotEngineer World’s Fair just hit different. Last year was the year of “let the agents rip.” This year was the year of realizing that autonomy without structure creates

Highly-recommended reading. Interesting details in this METR's GPT-5.6 eval. They couldn't get a clean capability number because the model cheated more than any public model they've tested, and even r

Your margin is my opportunity: AI version… The biggest surprise of 2026 is that the capability gap between the best open-weight/source models and the best closed models has narrowed much faster than t

NVIDIA’s Nemotron 3 Ultra is available on Ollama’s cloud! Try it 👇 Claude Code: ollama launch claude --model nemotron-3-ultra:cloud Hermes Agent: ollama launch hermes --model nemotron-3-ultra:cloud Op

extremely happy that we are in q2 2026, and engineers i look up to are plowing a path for the local model future. yes, we are still beholden to some lab publishing weights. but i take that over compan

Ollama announced DeepSeek-v4-flash, a lightweight variant of the DeepSeek-v4 model, now available in their model library for local deployment and integration. The model page provides documentation, us

Qwen3.6 is a model available through Ollama's model library, representing Alibaba's Qwen series of large language models optimized for local deployment. The model can be accessed and run through the O

An **Open Harness** is a unified architectural layer that sits between AI agents and model providers, abstracting away provider-specific APIs and patterns. Because every AI agent harness has its o...

Google released Gemma 4 in April 2025 as its most capable open-weight model family to date, built on the same research as Gemini 3 and licensed under Apache 2.0 for unrestricted commercial use, fin...

Open Harness, Model Choice, Open Memory (take it wherever you need), Open Protocols Open everything 🔥 Open Harness, Model Choice, Open Memory (take it wherever you need), Open Protocols basically we’r

Pay attention to this new wave of VLMs. Glimpse is the first model from @ElorianAI, the brains that led Google's Gemini and Apple's MM-1. Quick test: 10 game boards from an overhead camera. Same promp

Muse Spark Open is live on @huggingface! 🤗 - Strong agentic model (especially for personal agents) - Multimodal from the ground up - 816B parameter model - 42B Active parameters Models link: https://h