Search: “models”

🆕 The Full Story of Notion AI https://latent.space/p/notion We're so excited to chat with @simonlast and @sarahmsachs about Notion's 'Token Town' - the crack team of AI Engineers and Model Behavior En

For years, we’ve been building our cyber defense program on the principles of democratized access, iterative deployment, and ecosystem resilience. As model capabilities advance, our approach is to sca

Hermes Trismegistus is likely a language model released by Nous Research, continuing their Hermes series of fine-tuned models known for instruction-following, reasoning, and agentic capabilities. The

I'm excited about voice as a UI layer for existing visual applications — where speech and screen update together. This goes well beyond voice-only use cases like call center automation. The barrier ha

Open Harness 🤝 Deployed Agents if you wanna use Claude, GLM5, and Codex in your deployed harness then you should be able to! deepagents deploy has easy configs to let users customize their harness and

Time to follow http://hf.co/tencent! Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It

Folks, this is not Jevon's Paradox. this is just normal supply and demand. It turns out the utility of AI is high enough that people have high demand, which is outstripping supply (so prices will go u

Grok continues to lead global benchmarks: • #1 in AA Omniscience (lowest hallucination rate) • #1 in IFBench performance • #1 on BridgeBench Reasoning • #1 on BridgeBench Speed • #1 on BridgeBench Low

Memory operations, including retrieval, prioritization, compaction awareness, should be native and baked into the harness. 𝐖𝐢𝐭𝐡𝐨𝐮𝐭 𝐭𝐡𝐞 𝐩𝐫𝐨𝐩𝐞𝐫 𝐢𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐨𝐧 𝐛𝐞𝐭𝐰𝐞𝐞𝐧 𝐡𝐚𝐫𝐧𝐞𝐬𝐬 𝐚𝐧𝐝 𝐦𝐞𝐦𝐨𝐫𝐲, 𝐦𝐞𝐦𝐨𝐫𝐲 𝐚𝐥𝐨𝐧𝐞 𝐢𝐬 𝐩𝐨

Ollama version 0.20.6 has been released, featuring improved tool calling support for Google's Gemma 4 model. The update focuses on enhancing the reliability and functionality of function/tool calling

Marcus Hutchins, the cybersecurity researcher known for halting the 2017 WannaCry ransomware attack by registering a kill-switch domain, is cited as offering a notable perspective on AI systems conduc

OpenAI's Codex App (available at chatgpt.com/codex) is a dedicated command center for agentic coding, enabling developers to manage multiple AI coding agents working in parallel across projects. T...

GLM-5.1, developed by Z.ai (formerly Zhipu AI), is Z.ai's next-generation flagship model for agentic engineering, featuring 'significantly stronger coding capabilities than its predecessor,' bette...

I was unable to retrieve the specific content of the linked tweet, as X (formerly Twitter) requires JavaScript and login to display individual posts. The search results did surface a highly relevan...

La France a parmi les meilleurs mathématiciens et ingénieurs IA du monde. On le sait. On les embauche partout ailleurs. Et la première chose qu'on fait au moment où on pourrait enfin capitaliser dessu

1️⃣✅❌ 2️⃣✅❌ 3️⃣✅❌ One of the benefits of Deep Agents deploy is model optionality Choose from models from @OpenAI @GeminiApp @AnthropicAI @FireworksAI_HQ @baseten @OpenRouter @ollama @nvidia and many o

Grok is the AI to use if you value truth Grok 4.20 Non-Hallucination rate improved to even higher than previous highest Just days ago, it hit a record-breaking 78% Non-Hallucination Rate - already #1

The specific tweet (status ID 2042224314494161089) was not directly retrievable from search results, but the broader context of the 'Is OpenAI trying to become Anthropic, while Anthropic becomes Op...

memory ownership is why we need open harnesses blog about this coming this weekend The memory ownership point is the real story here. Running a persistent agent 24/7, memory isn't a feature — it's the

most of the agents we see being built do this the main cases where we see people using 'agent in a sandbox' is when they are using claude agent sdk (which is poorly designed for 'harness outside sandb

I was unable to retrieve the specific content of that X (Twitter) post from Anthropic. The URL provided (https://x.com/Anthropic/status/2042389901895766021) points to a tweet sharing a Wordle 1,755...

Claude Mythos is Delusional Media Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Previe

ComfyUI hosted a live broadcast on April 8, 2025, titled 'Control ComfyUI with Claude Code,' demonstrating how to queue workflows, tweak parameters, and automate an entire generation pipeline with...

Author Kurt Andersen posted on X (formerly Twitter) that Pete Hegseth has become 'indistinguishable' from SNL's Colin Jost parody of him. SNL's Colin Jost has repeatedly parodied Pete Hegseth, Tru...

It seems like the day has come to leave Anthropic. Initially, I loved Claude Code. It was a good harness and a simple TUI... and I had learned to eat my tokens with a sauce of subsidy. Before joining

Let's see how MiMo V2 Pro evolves in Hermes Agent! We have partnered with @Xiaomi to bring their excellent MiMo V2 Pro model to Hermes Agent via the Nous Portal - completely free to use for the next 2

Proud to power @NousResearch's Hermes Agent with MiniMax M2.7, and excited for what we're building together. Try MiniMax M2.7 in Hermes Agent today → https://portal.nousresearch.com #MiniMax #NousRese

Sebastian Raschka (rasbt) used Randal Olson's Tufte Test tool, developed by Goodeye Labs, to improve the visual quality of a machine learning benchmark plot. The Tufte Test encodes seven of Tufte'...

'The priority for defenders is to start building now: the scaffolds, the pipelines, the maintainer relationships, the integration into development workflows. The models are ready. The question is whet

【速報】中国のAI企業http://Z.ai（旧Zhipu AI）が最新AIモデル「GLM-5.1」をリリースしました🚀 コーディング性能を測る「SWE-Bench Pro」で58.4%を記録し、オープンソース（誰でも無料で使える形）モデルとして世界1位。全体でも3位（GPT-5.4の57.7%を上回る）という強力なスコアです📊 最大の特徴は「長時間タスクで力を発揮する」点👇 🧠 8時間にわたって

I was told about the Mythos release, but didn't have access, so have no personal experience to add. Two points from brief: 1) It is not built for IT security, it is just a good enough model that it is

The chart says GLM-5.1 scored 54.9 on coding benchmarks. Three points behind Claude Opus 4.6. Interesting but not the story. The story is what trained it. Zero Nvidia GPUs. 100,000 Huawei Ascend 910B

**Ollama Cloud** provides a cloud-hosted model serving platform that *never retains user data* ('zero data retention') and does **not train on any incoming data**. The infrastructure is distributed ac

Three years and seven months ago, we could only send AI 50 messages every 4 hours to GPT-4. GPT-4 had a token cap of 8k/32K. Astra has 1M. GPT-4 scored a 39% on GPQA Diamond. Astra scored 96%. Sometim

Seriously, there is no way to algorithmically filter out the obvious AI slopreplies? The paper on how a team of Gemini 4 agents beat Minecraft is worth a look. It is accessible example (partially beca

Mistral AI introduced a tool aimed at high‑energy physics that can reconstruct particle collisions, identify particles, flag unexpected signals, and evaluate future detector designs. The announcement

multiple release by nvidia today, love how they compress nemotron 3.5 super to the 'perfect' size for their specific hardware (RTX spark). there is a full tech report, including how they use their own

We want to support the mathematics community in turning progress in AI into deeper human understanding and new discoveries. To support that goal, we are contributing 5 million to a new Simons Foundati

Gemini 4 Argon, Muse Spark 1.3, and Muse Wonder 1.0 are all really good at pdf parsing. Come check it out on OpenDocRouter! https://www.opendocrouter.ai/ Media OpenDocRouter makes it dead-simple to st

New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL environments. They show that Qwen3.6-35B-A3B goes from 41.1 to 53.3 on Terminal-Bench 2.1 by trainin

Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the mode

Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro

wait so this feels a bit different too in a good way You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models

The Bitter Lesson for harness design and formal math! Instead of hand-designing how an AI should prove (decompose, plan, assign agents), what if we just give a frontier model good Lean feedback and le

Build your own harness, folks. Reading papers like this makes me realize how underexplored harness engineering really is. The authors find that on whole-repository migration, GPT-5.6 Sol goes from 6.5

Bullish on this trend of making post-training more accessible. A new post-training era is upon us. If you work on agentic RL, long-context tasks (a big focus today) are expensive, inefficient, and don