Search: “papers”

Grok 4.3 has introduced native LaTeX compilation functionality integrated directly into Grok Files, enabling users to compile LaTeX documents without requiring external tools or applications. This fea

Plugins for Excel, PowerPoint, Word, … coming soon Academics, business leaders, and anyone stuck making PowerPoints: Grok 4.3 just turned a full tDCS/TMS neuroscience paper into this clean 9-slide aca

Training code and models are live on Hugging Face. Dan Fu (Together AI's VP of Kernels) led the work. Together AI provided compute. Blog: https://www.together.ai/blog/parcae Paper: https://arxiv.org/a

LLM Knowledge Base → Slides When @karpathy shared his LLM Knowledge Base setup, many were wondering how to generate more visual forms of the wiki. There are many options, but I think @GammaApp is one

This skill is now built in to Hermes! Use /architecture-diagram <prompt> after updating hermes, and you're good to go! Thanks to the author of the skill making it MIT we were able to port it over dire

Microsoft's AI can now detect cancer from a $10 tissue sample. For context, every time tumor cells are tested, doctors create a basic microscope slide to study tissue up close. These slides show cell

This Japanese blog post explores whether signs and symbols can emerge within a single neural network, drawing on analysis of the 'Neural Computers' paper. The discussion likely examines the intersecti

The model is not the agent. The harness is. You need to read this recent study, and a blog post from @hwchase17 ... (links below). It will resonate deeply. This diagram from a recent paper captures so

Agents need a better interface. In my own agent orchestrator, I often render more actionable, valuable outputs as small interfaces. @openuidev makes this easy for any AI app. It is an open-source, mod

The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery Blog: https://pub.sakana.ai/agentic-scientist/ GitHub: https://github.com/SakanaAI/AI-Scientist-v3 arXiv: htt

The AI Scientist v3 is out: The Agentic Scientist. GitHub: https://github.com/SakanaAI/AI-Scientist-v3 Blog: https://pub.sakana.ai/agentic-scientist/ arXiv: https://arxiv.org/abs/2610.18933 The Agenti

What AI Safety needs is better tooling and engineering. For instance, building stronger red-teaming tools. Great to see this open-source effort to red-team image models. It seems to learn better ways

OpenAI math problems are now open source RL environments We’re releasing a broad range of new mathematical results produced by an internal frontier model. We’ve been consulting with the independent Ad

Huge release from @odysseyml. Odyssey-3 Pro sets a new top score on Physics-IQ Verified, a benchmark that asks models to continue videos of real physics experiments. The robotics results stood out to

Reading eval results is now the slowest part of building agents. I'm Elvis, founder of @dair_ai. I lead research, build, and teach about AI agents. I run harness experiments every night, but reading t

Great report from Google and MIT. Co-designing ML models and the accelerators is an exciting research direction. This report introduces Coco, an agent platform TPU architects use for hardware and mode

Like Jev, I believe RL will unlock several more like this, slashing the cost of critical agent operations. flow-1 is competitive in performance, but a huge cost-saver for finding failures in agent tra

Learn to build a custom harness, folks. Mods in Claude Code, DeepSeek Harness, and now Pi Durable. What do these all have in common? Increased extensibility. Builders need coding agents and harnesses

Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the

Code review has to change for coding agents. Why? For me, it’s about scaling coding reviews while ensuring quality. If you give a coding agent one task, it can return several pull requests across diff

On September 29, 2026, Twitter user Severin Field (@sevdeawesome) posted that an AI‑generated video from Claude 5.5 Opus responding to the phrase “AI is a normal technology” was the best AI‑created vi

worst these will ever be 3:26 section is a good example of super persuasion incoming right in the kokoro Made with Claude Opus 5.5. The fearmongering about AI always makes us forget that NOTHING WENT

Cool to see classification models resurge in the era of agents. The effects of Jev are insane. Also very cool to see our emotion dataset built at @dair_ai used to test this new model, Julia-1. I spent

This is brilliant. Recommended reading. It's a great example of how you could potentially build more effective harnesses using System One and System Two models. It explores Jev's potential as a fuzzy

I agree. Learn the fundamentals, folks! If you plan to be a solid builder using agents, this is a really important point. There is no way around it. I have recently started digging deep into evals, in

Exciting work from NVIDIA. (bookmark it) Interesting to see this approach to turn public Agent Skills into RL environments. Lots of excitement around RL environments so this is a great read. Skill2Env

Finally, a company brain that actually works! Codos starts with the people doing the work. It interviews employees to find which tasks can be automated, then deploys the automations and keeps learning

lots of them! Reality is that LLM APIs are far from being the best way to do AI for 90% of use cases in the real world (they're too overkill, slow, expensive, hard to control,...). We will discover th

breaking: author of the study that so many “AI influencers” are taking as evidence that LLMs feel pain tells me “we don’t claim they feel pain.” The good news is that the author understands correctly

I think there are lots of good reasons to worry about whether AI is giving correct answers (especially free models), but, given the contradiction with other recent research suggesting AI is now doing

LlamaIndex 发布了一个面向 AI Agent 的文档解析评测基准「ParseBench」 @llama_index 100 种解析方法参与评测（vlm - 67、专用解析器 - 33），2000 页真实企业文档（人工两轮校验），169011 条确定性规则，完全不用 LLM 当裁判，可复现。评测五个维度取无加权平均：表格结构、图表抽取、内容忠实度、格式语义、视觉定位。 https://ww

Banger release from NVIDIA. They just published a report on NeMo Data Designer, their open-source synthetic data tool. It's a declarative config which makes a synthetic data pipeline easy to review, s

Rene has a really neat multiplayer agentic experience. I run several agents at once. So I lose track of important conversations throughout the day. Rene pulls conversations from my inbox and manages t

Introducing PC-ALM, a local-learning alternative to backpropagation. Our method trains 1000-layer neural nets using only local dynamics, and without backprop. Blog: https://pub.sakana.ai/pc-alm/ Stand

Well, I’d add one more with myself, as one with a PhD in biology and another PhD in AI and now working in both, to make n=2. Generating a hypothetical genome blueprint of a virus from LLM versus gener

【AIの難問は、生命の難問へ：英国王立協会が紐解く「世界モデル」と知能の未来】 近年のAIの急速な発展により、AGI、すなわち人間並みの知能はすでに実現したという意見も聞かれるようになりました。果たしてそうなのでしょうか。 鍵となるのが「世界モデル（World Model）」の概念です。 世界モデルとは、生き物やAIが外の世界を内部に写し取り、次に何が起きるかを予測して行動するための土台となるもの

Does anyone have any idea how this could vaguely be possible given the nature of and various routes to RSI? I am not being facetious I genuinely don’t know how this could be constructed or implemented

Looped transformers are a popular architecture topic right now. This new technical report extends the loop across tokens. Recurrent Looped Transformer (RLT) makes the decoder recurrent over every toke

Recommended read. As the world becomes more agentic, we will start to see world models of different shapes. As an example, I find this “business world model” from @lightfld fascinating as a way to mod

This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m

// From Language Models to World-Acting Systems // A critical review of agentic AI, and a framework that is genuinely useful for deciding how much authority to hand an agent. Here is how it works. The

Great tips on working with reasoning models. Normally you would append what the model figured out after the document and ask again. It turns out that where you put the reasoning trace changes long-con

This work introduces diffusion-augmented LLMs, a new class of models. They first suggest that speculative decoding needs a separate draft model. Diffusion LLMs give up the quality of the model they re

Can a strong general-purpose vision model distinguish real from AI-generated images using only a simple decision rule on frozen representations? Our latest results, to be presented at #ECCV2026, show

Impressive tool to explore frontier AI capabilities. Martian's AI Frontier lets you compare 44 LLMs by measured cost, quality, and reliability, then see how routing and repeated sampling change the fr

A lot of hype around OpenAI's Astra model here on my timeline today. Apparently, this goes back to a new article from The Information, which said Astra is a 'recurrent depth or looped transformer'. It