Search: “deployment”

As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for

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

Some thoughts on Dario’s post: 1. Dario does not actually address Gavin Baker’s account of what he said – something he could easily deny if it were inaccurate. 2. Dario claims his critics live in a “b

Fantastic initiative by @nvidia. “Circular financing” is thrown around as a pseudo intellectual gotcha, while everyone in the AI infrastructure business is witnessing demand curves that are so rapidly

1/2 Thanks Gavin for an especially thoughtful exchange. I don't usually spend much time on social media but I wanted to engage here because it really brings out the heart of an important conversation.

CONFIRMED: @c_valenzuelab, cofounder and co-CEO of @runwayml, is speaking at Thesis, our inaugural conference on work and AI. Language models predict the next token, aka the next unit of text. Runway’

We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world

A great read if you an AI dev. Current context compactors retain 17% of the standing rules users give them. Session Constraints are instructions like 'do not delete any emails until I confirm' that bi

Our UK reps didn’t remember to smile 😂 We recently opened a @llama_index office in London 🇬🇧. It is three people strong (Frank, Max, Joe), with two more people starting soon. It also has a beautiful v

out of curiosity, i tasked fable to figure this thing out and it looks like the 'saas killer' is done. ▲ it maxed out Fable 5 + used most of Codex limits ▲ most of the work was done within 45h session

There is much less signal in agent leaderboards than the rankings imply. A four-facet Generalizability Theory decomposition across TheAgentCompany, tau-squared-bench, and AppWorld finds the agent main

The article explores how businesses are embedding AI into daily operations, emphasizing the rise of *agentic* (self‑directed) workflows that span multiple industries and job functions. It highlights t

Burke Holland announced that the Qwen‑3 Coder 30B model was running locally through GitHub Copilot’s Ollama integration, achieving roughly 85 tokens per second while utilizing 96 GB of VRAM. He noted

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

Impressive new paper from Meta. (bookmark it) Scaling laws assume model size and training data act on loss independently. This work introduces Skaling law, which couples capacity and data through a si

We’re expanding our cybersecurity initiative Daybreak and introducing GPT-5.6-Cyber, a new model for advanced, authorized cybersecurity work. As the threat landscape evolves, we’re putting frontier in

New research from Meta. Agent harnesses are still mostly authored by hand. This makes it hard to tune robust agent harnesses for long-horizon tasks. In this new work, agents learn harness policies off

You don’t need new ways to talk to your agents, you need new ways for your agents to talk to you 🫵 (do you?) Introducing Remoko: your mobile agent relay http://remoko.app I wanted a way for my long-ru

Uber burned through its 2026 AI coding budget in four months. Microsoft canceled most of its Claude Code licenses six months after rolling them out. The mechanics are simple: per-token cost keeps fall

To give some more context on what we are building with Daiwa Securities: During our technical verification phase, we integrated our AI agent technologies, specifically our AI Scientist and AB-MCTS fra

Building agents that patch other agents. This is an interesting approach for self-improving agents that leverages agent outputs. If you run agents in production, you already have the training data for

Today, we’re launching Alpamayo 2 Super, our frontier open reasoning model for autonomous vehicles. Beyond seeing, Alpamayo understands and reasons through the complex world - thinks before it acts. I

Horiyuki 'horiyuki42' joined Sakana AI Labs in August 2026 as an Applied Research Engineer Intern. He plans to work full‑time during the university summer recess while concentrating on large‑language‑

Qwen from Alibaba has released the Qwen 3.8‑Max model on the Venice platform, enabling users to ask questions anonymously. The announcement encourages users to try the new functionality immediately. T

OpenAI has redesigned the ChatGPT Voice stack—from client to model—to enable continuous audio streaming, allowing GPT‑Live to listen while speaking without interruption. The new architecture supports

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

Kimi K3 has set a new bar for OSS model intelligence! 2.8T params, 1M context, OpenAI-compatible API. Complete guide to running Kimi K3 on Together AI 👇 👏👏 @Kimi_Moonshot 👏👏 https://www.together.ai/bl

I'm actually fairly bearish on frontier lab valuations. I've never seen the reasons articulated to my satisfaction, so before I go to sleep, I wanted to quickly jot down my thinking here. The basic is

On benchmarking long-context agentic instruction following. Agent benchmarks mostly reward reaching the answer. This new benchmark measures whether the agent reached it the permitted way, which is the

Two of the people most responsible for scaling the transformer are now betting on a next act. @MillionInt ran the Reasoning 🍓 team at OpenAI. @_arohan_ was a pre-training lead on Gemini after years at

We hope these experiments serve as a reminder that evals rarely measure models in isolation—they also measure a bundle of less visible choices about API settings, harness design, and prompting. If you

We ran a large-scale distillation attack on the Kimi K3 technical report by reading it in parallel at the Hugging Face Journal Club :) https://youtu.be/MW8-kqd2SD8?si=jSKDogcUWbJ8N2k7 Our main takeawa

Code Arena now measures fullstack capabilities! View overall rankings across AI models on full-stack web development tasks: multi-step reasoning, tool use, and end-to-end app generation. - Kimi K3 (Ma

The LangChain podcast where @hwchase17 interviews agent builders is full of alpha. Recent one with @EnoReyes was the best one yet. Sharing my unstructured notes: Eno keeps bringing back some core conc

Together AI has released the Kimi K3 model on its platform as a Day‑0 launch partner for Moonshot AI’s open frontier agentic model, which supports long‑running workflows across code, tools, vision and

We're proud to join @NVIDIA and the Open Secure AI Alliance. To support open source models, we're contributing our research on measuring the trustworthiness and security of open source models. Closing

Geoffrey Hinton says a big language model runs on about 1% of your brain's connections and still ends up knowing more than you: 'So in your brain, you have a hundred trillion connections, roughly spea

New research with Microsoft's and colleagues on training agents inside the harnesses they actually run in. (bookmark it) Why it matters: Agents today live inside elaborate harnesses like Claude Code,

Most AI SDKs are a wrapper around one engine on one platform. We built the opposite. 7 SDKs. Swift, Kotlin, Flutter, React Native, Web, Electron, rcli. Python. All of them are thin skins over one C++

As AI models are now finding vulnerabilities faster than we can fix them, our approach to securing software must be built on highly efficient and capable models. Which brings us to our third (!) model

Great article. I love the 'CERN for AI' idea from Gary Marcus, and also the recent frontier standards body article from Demis Hassabis feels less like competing proposals than two halves of the same i

Mistral is announcing an expanded global strategic partnership with @Microsoft to give enterprises and regulated industries frontier AI they can control. As Mistral is expanding its AI compute capacit

Run Devin Outposts on @nvidia Brev to give Devin access to GPU infrastructure for debugging training runs, inspecting GPU state, reproducing failures, and validating fixes on the hardware where the wo

Together AI’s recent fireside chat with Y Combinator’s Andy Gupta explains why speed to launch and scalability were the key factors in selecting a partner for YC’s first dedicated GPU cluster. The con

“I asked a few AI researchers whether they could name any other real-world software that scales so poorly. None of them could think of any. Even outside the world of software, it’s hard to find a comp

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 se