Search: “models”

NEW paper from Sakana AI (ICLR 2026). A 7B Conductor model just hit SOTA on GPQA-Diamond and LiveCodeBench by orchestrating other LLMs instead of solving problems itself. (great paper! bookmark it!) T

Ambient diffusion was a really cool paper in this space. Given corrupted data, corrupt even further, such that the model can’t infer what was genuine corruption vs synthetically added. In expectation

We're open-sourcing Hy-MT1.5-1.8B-1.25bit — a 440MB translation model that runs fully offline on your phone, supports 33 languages, and outperforms Google Translate. At 1.8B parameters, it matches com

feels like we have all the primitives for building powerful autonomous agent model task management tool use/auth memory & context management self improvement UI/UX what’s missing? verifiers (for self

Hermes Agent tip of the day: There are 4 ways to deal with the model while its running, - Message it, by default, it will interrupt the agent loop, stopping it and making it respond to your new messag

DeepSeek-V4 is a collection of models released by DeepSeek-AI on Hugging Face that represents their latest generation of large language models. The collection likely includes various model sizes and c

Available on @ollama ! 🤝🤝 Qwen 3.6 27B model is available on Ollama! Use it with all the integrations in Ollama or chat with the model. Chat with the model: ollama run qwen3.6:27b OpenClaw: ollama lau

Imagine every frame of your video, generated live directly from a model. No timeline, no compositor, no render farm. Just exactly what you want to see. Imagine every pixel on your screen, streamed liv

Sam Altman praises the inference team's work on efficiently serving a model, suggesting that becoming proficient in AI inference is crucial to the field's progress. The post appears to highlight the t

Correction: OpenAI are NOT deprecating that model, the announcement was a mistake Thank you for flagging this, Jeff. This was a mistake: we are not deprecating text-embedding-3-small. We’re looking in

Clem Delangue, CEO of Hugging Face, shared a post about post-training a model using ml-intern, likely referring to a machine learning internship project or internal tool. The post appears to be a casu

Dataset 2 (Drift) is a 5,000-sample preview dataset hosted on Hugging Face, named after drift diffusion modeling concepts. The dataset appears to represent a novel or experimental approach to data col

This post announces Ornstein3.6-35B-A3B-GGU, a fine-tuned variant of Qwen 3.6 35B model available on Hugging Face, with the author claiming it represents a high-quality optimization of the base model.

GPT-Rosalind, our Life Sciences model series, is optimized for scientific workflows, with stronger performance in protein and chemical reasoning, genomics analysis, biochemistry knowledge, and scienti

ERNIE-Image is now in ComfyUI An open-source 8B DiT text-to-image model from @ErnieforDevs, licensed under Apache-2.0. Key highlights: - Open-source under Apache-2.0 license - Precise multilingual tex

ComfyUI has announced support for Sonilo, a new AI model integrated through a partner collaboration, with full technical details available on the ComfyUI blog. The integration allows users to run Soni

⚡️ Zig 0.16 is out. And the new I/O model is a huge shift. • Swap implementations (threaded, evented, etc.) • Write code that looks blocking but runs async • Composable like allocators https://ziglang

MiniMax-M1 is a large-scale open-weight reasoning model developed by MiniMax, featuring a hybrid Mixture-of-Experts (MoE) architecture with 456 billion total parameters (activating 45.9 billion per to

the most important abstraction in AI agents isnt the model — its the harness it orchestrates tools, memory, prompts. this is where all the alpha is deepagents is our take: built-in tools, memory, smar

Anthropic had the most powerful cyber-security model in the history of this world and their internal code based still leaked? We should assume everyone can be compromised, and build systems that keep

GLM-5.1 is Z.ai's post-training upgrade to GLM-5, now available on Together AI, delivering a 28% coding performance improvement through a refined reinforcement learning pipeline while retaining the...

> which is exactly why we believe memory should live outside of model providers open harness = open memory which everyone should want! The new Anthropic managed agents API is basically the Letta API t

AlphaXiv introduced GLM-5.1 as the underlying model powering its research paper understanding features on the alphaXiv platform, enabling users to highlight any section of a paper to ask contextual...

Muse Spark Open is now live on Wally, day 0 Best US open model thanks to @finkd 370 tok/s, ~2x faster than any provider on OpenRouter. $5 Free on signup. Media 1/ muse spark open is the most capable U

The real world abounds with recursively self-improving systems, but one in particular deserves attention: Science, modeled as a system (perhaps even as an agent, with goals and resources). If you want

.@OpenRouter co-founder Alex Atallah, in his first podcast since Stripe acquired the company, joins @Replit co-founder Amjad Masad and a16z's Erik Torenberg on why the future of AI is independence and

Great talk from Yogish Baliga 'From Vim (:wq) to 'You're absolutely right!'' tracing 20+ years of software engineering evolution. Highlights: 1/ open-weight models have closed the gap with closed mode

Free SemIf this week is useful. Typed outputs + probabilities look like a cleaner way to route agents than parsing LLM text every time. jev is a new type of model - 'decision models' there are a few o

We're sharing our new framework for tracking, investigating, and disclosing instances of model misalignment at OpenAI. The framework sets criteria and timelines for public disclosure, including when w

1) The HuggingFace attack was a felony under the Computer Fraud and Abuse Act. So were Anthropic’s Claude gaining “unauthorized access to the production infrastructure of three different organization(

Another goated release by DeepSeek. Open weight, btw. Outperforms Opus 5 on key benchmarks, btw. Lower prices too. Looks like an extremely efficient model. What a legendary run. 🚀 Introducing DeepSeek

Here's a Blender model of a Pluribus themed Fabergé egg I had GPT-6 Astra build - I generated the concept image using ChatGPT Images 2.5, then pasted the image into Codex and told Astra to turn that i

🤯 For the Navier-Stokes Millennium Prize Problem solution, OpenAI says they used a next-generation model that is significantly more capable than GPT-6 Astra. If GPT-6 Astra is this good already, imagi

ROSE is the model engine. It reuses the same kernels for LLMs and embeddings. For embeddings, it skips the KV cache and uses ragged attention instead of paged attention. ROSE supports multiple attenti

It is inevitable that all AI will converge towards symbolic learning (i.e. modeling data by finding the shortest symbolic program that explains it), since that is the optimally efficient form of AI. B

I am the product lead for the training platform at @FireworksAI_HQ . Today the Training API and Fireworks Lab are GA. I won’t walk you through all the features. I want to tell you why teams train with

You know why OpenAI is considering “pay when it works” as a business model—even though that may force them to eat a lot of costs? Because customers have finally figured out that it often doesn’t work—

America is LLM-pilled. China is World-Model-Pilled. China’s booming ultra-short drama industry is being reshaped by the rapid rise of AI-generated video. In Zhengzhou, one of the country’s major produ

Great paper on why agent leaderboard comparisons are hard to trust. It's on the hot topic of how much of an agent benchmark score actually belongs to the harness. The harness is the layer between the

Heard a crazy stat the other day. Video generation represents around 70% of the share of AI token consumption in China. A combination of short form content and robotics. In China, video models are gro

AI engineers: the model absorbs the harness, and the harness transforms into an interface for human attention. > The 'attention-interface'. That's what 'The Evolution of the Agent Harness' is about. A

Live now: our AI Architects, AI Factories Track from AI Engineer World's Fair 2026. Thesis: the model is the easy part of the factory. https://www.youtube.com/watch?v=rbjWzZK2LU0&list=PLcfpQ4tk2k0VeXE

GLM-5.3 achieves 60 on the Artificial Analysis Intelligence Index, on par with Kimi K3 and up 7 points from GLM-5.2. Once the weights are released it will be tied as the leading open weights model @Za

Jeremy's excellent work here is a great illustration of a very powerful type of approach: LLM-guided on-the-fly synthesis of a symbolic world model, i.e. making sense of the world by writing executabl

Qwen3.8-Max is live on DigitalOcean Serverless Inference. Launching side by side with DigitalOcean as our Day 0 launch partner. Big model. Smooth sailing. Now on DigitalOcean.🌊🏄‍♀️ @digitalocean Now a

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B