Introducing TALES - Text Adventure Learning Environment Suite A... benchmark of a few hundred text envs: science experiments and embodied cooking to solving murder mysteries. We test over 30 of the best LLM agents and pinpoint failure modes +how to improve 👨‍💻pip install tale-suiteshow more

I don’t know if you noticed, but the last... few versions of Codex Remote went from jumpy scrolling to smooth streaming. I really like how it turned out. And also, the best way to test and debug that? Ask Codex for an endless wall of text.show more

react-native-enriched 🤝 <EnrichedText> We just dropped a dedicated text... component, making it a complete rich-text solution. Now it only takes a few lines of code to get your inputs and display text working seamlessly together using the exact same format.show more

A two-person team with agents now out-ships a company... of 20, but few can tell you how. The workflows live inside a couple hundred minds. We talk to them daily, and today we're unlocking their brains. Introducing cyber•OS: the open knowledge base for building AI-native.show more

We are releasing AutoResearchExam, a benchmark on open-ended machine... learning and engineering tasks. Our benchmark covers seven research areas including model training, data curation, AI safety and interpretability. In each task, we give agents 24 hours with a CPU or GPU machine to develop and improve their solutions through experiments and feedback. We measure both speed and quality with a combined score. Our benchmark has a unique feature: testing if agents create improvements that hold up on data they never see. We find that AI research agents often overfit as they try to improve. We see an interesting head-to-head comparison at the frontier: Astra starts the strongest and holds the lead for up to 19 hours but Fable 5.1 catches up and gets the top performing spot in the final hours. Qwen3.8 Max, Gemini 3.8 Flash and Grok 4.6 all sit on the cost-performance Pareto frontier, giving strong options at lower API budgets. Anthropic's Opus and Fable retain nearly all their validation performance on hidden tests, with gaps of 1.1% and 2.9%. Astra's improvement over Sol extends to generalization too, with that gap falling from 6.9% to 1.7%. (1/n)show more

Get beautiful text animations. We built a hand-crafted collection... of text animations and wrapped them as a SKILL for your AI agent. Use it with Remotion, Motion, GSAP, WAAPI, or any animation library. It comes with clear animation specs - pacing, curves, transitions - so your output looks great from the first prompt. Install it with: npx skills add pixel-point/animate-text --skill animate-text Use it /animate-text apply soft-blur-in to hero section textshow more

We are investing in the frontiers of agentic capabilities... with a few early prototypes. Project Mariner is built with Gemini 2.0 and is able to understand and reason across information - pixels, text, code, images + forms - on your browser screen, and then uses that info to complete tasks for you. When evaluated against the WebVoyager benchmark, it achieved a state-of-the-art result of 83.5% working as a single agent setup.show more

We’re excited to released our first DocC interactive tutorial... for the Composable Architecture. It walks you through the basics of creating a feature, layering on some side effects, and writing a full test suite. And we have more coming soon! 👉show more

We’re excited to introduce Text-to-LoRA: a Hypernetwork that generates... task-specific LLM adapters (LoRAs) based on a text description of the task. Catch our presentation at #ICML2025! Paper: Code: Biological systems are capable of rapid adaptation, given limited sensory cues. For example, our human visual system can quickly adapt and tune its light sensitivity to our surroundings. While modern LLMs exhibit a wide variety of capabilities and knowledge, they remain rigid when adding task-specific capabilities. Traditionally, customizing these models requires gathering large datasets and performing often expensive, time-consuming fine-tuning for specific applications. To bypass these limitations, Text-to-LoRA (T2L) meta-learns a “hypernetwork” that takes in a text description of a desired task, as a prompt, and generates a task-specific LoRA that performs well on the task. In our experiments, we show that T2L can encode hundreds of existing LoRA adapters. While the compression is lossy, T2L maintains the performance of task-specifically tuned LoRA adapters. We also show that T2L can even generalize to unseen tasks given a natural language description of the tasks. Importantly, Text-to-LoRA is parameter-efficient. It generates LoRAs in a single, inexpensive step, based solely on a simple text description of the task. This approach is a step towards dramatically lowering the technical and computational barriers, allowing non-technical users to specialize foundation models using plain language, rather than needing deep technical expertise or large compute resources.show more

fun little drag control for a side project i’m... tinkering on i’ve seen a few versions of this around and wanted an excuse to make one myself a few details: overdrag, the notch fades as you scrub over the values, text inverts to stay legible, and there’s even a color-adaptive input fieldshow more

Microsoft presents Windows Agent Arena Evaluating Multi-Modal OS Agents... at Scale discuss: Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in realistic environments remains a challenge since: (i) most benchmarks are limited to specific modalities or domains (e.g. text-only, web navigation, Q&A, coding) and (ii) full benchmark evaluations are slow (on order of magnitude of days) given the multi-step sequential nature of tasks. To address these challenges, we introduce the Windows Agent Arena: a reproducible, general environment focusing exclusively on the Windows operating system (OS) where agents can operate freely within a real Windows OS and use the same wide range of applications, tools, and web browsers available to human users when solving tasks. We adapt the OSWorld framework (Xie et al., 2024) to create 150+ diverse Windows tasks across representative domains that require agent abilities in planning, screen understanding, and tool usage. Our benchmark is scalable and can be seamlessly parallelized in Azure for a full benchmark evaluation in as little as 20 minutes. To demonstrate Windows Agent Arena's capabilities, we also introduce a new multi-modal agent, Navi. Our agent achieves a success rate of 19.5% in the Windows domain, compared to 74.5% performance of an unassisted human. Navi also demonstrates strong performance on another popular web-based benchmark, Mind2Web. We offer extensive quantitative and qualitative analysis of Navi's performance, and provide insights into the opportunities for future research in agent development and data generation using Windows Agent Arena.show more

Avalanche meets DeFAI: Introducing AIvalanche DeFAI Agents Backed by... Avalaunch, Aventures DAO and more. #AI is exploding to a $15 trillion market. The most profitable economy in history. Crypto is on path to break the $10 trillion mark. #DeFAI fixes crypto’s biggest pain point: ease of use. These AI tools allow anyone to use AI agents to navigate the complex world of swaps, yields, and staking – with simple voice or text commands.show more

Nashville Supercross 🤠 I booked a suite and watched... the races with old and new friends last night. Throughout the night dozens of people stopped by to watch - the Dirt Bike Depot team, Joan Cros and his mechanic Michael, and @SouthernPuddles and @RealMrPuddles. At one point, I counted over 20 people in the 18-person suite 😄 it was an awesome environment to watch the night show! I got to listen in on the DBD team headset during Linville’s LCQ ride. What a great ride from him, especially in an East West showdown. 👏 I took very few pictures yesterday and don’t really care 😂 I was too busy enjoying myself lol.show more

We are getting absurdly close to the point where... “learning Blender” means learning how to direct an AI. A shot like this looks soft and playful on the surface, but under it is the usual 3D pain: modeling, layout, materials, lighting, atmosphere, animation, and endless tiny fixes until the frame stops looking dead. That is why Kimi K3 matters. With Blender MCP, you can describe a scene like a robotic goat walking through a dreamy field and let the model help build the environment, place the camera, shape the materials, script the motion, and iterate inside the real Blender project. The real shift is not text-to-image. It is text-to-workflow. Kimi K3 does not just give you a pretty output and disappear. It can help move the actual scene from rough setup to something that looks art-directed. Soon the hardest part of 3D will not be the software. It will be whether your imagination is good enough to deserve tools like this.show more

PhD Students - How to detect AI text in... your writing? We often use ChatGPT for writing. However, this leads to AI-plagiarized text. This can be problematic in many scenarios. For example, if you use AI text in your papers. Your research paper can get desk rejected. 🍁How to detect if there is AI text in your writing? 1. Go to and log in. 2. Click on 𝐴𝐼 𝑑𝑒𝑡𝑒𝑐𝑡𝑜𝑟 from the left menu 3. Insert your text and click on 𝐴𝑛𝑎𝑙𝑦𝑧𝑒. 4. will generate AI detection report This report shows the following. → Percentage of AI generated text → Options for converting AI text into non-AI text 🍁How good is this AI detector? SciSpace conducted a benchmarking study. In this study, the detection capability was compared with other AI-detectors. SciSpace AI detector was tested with 4000 samples. It showed an accuracy of 96%. This means it can detect AI-generated text with 96% accuracy. The study showed that SciSpace AI detector has outclassed AI detectors like GPTZero, ZeroGPT, and Grammarly. 🔴Anything you'd like to add?show more

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper... page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.show more

Artificial embryo samples aboard Tiangong Space Station for life... science research Space "artificial embryo" samples and other life science experiments delivered by the Tianzhou-10 cargo spacecraft have been installed into experiment modules aboard China's Tiangong space station, the Technology and Engineering Center for Space Utilization under the Chinese Academy of Sciences (CAS) said on Wednesday. The "artificial embryos" are stem cell-derived artificial human embryos. The embryos, though not true life forms and unable to develop into human babies, will help simulate the earliest stages of human development. Once the experiments are completed, the artificial embryo samples will be frozen in orbit and then returned to Earth on a future mission for side-by-side analysis with ground-based controls in laboratories on the ground. This effort is part of a broader suite of 41 space science experiments being deployed aboard Tiangong, supporting its latest round of research on the orbiting laboratory.show more

in software, we're entering a new age of skyscrapers:... rather than a small group of humans hand-typing code into a computer, software is now built by thousands of humans and agents working together to build applications at a scale that was previously unthinkable. the unsung heroes of this new era are infrastructure engineers. they are the people who are figuring out how to make software with 100x the amount of code, and 1000x the amount of contributors actually work OpenAI is one of the few companies already operating at this scale so we Every 🪨 spent a few days deep inside of the company to learn how their infrastructure team thinks about building software skyscrapers—and how they use agents to do it one of the most important articles we've written this year:show more

Introducing SVG Arena! SVGs are XML-based text files that... encode geometry, and they're surprisingly tough for state-of-the-art LLMs to get right Here's how bad models (still) are at drawing a pelican on a bicycle - creds to Simon Willison Leaderboard coming soon! In the meantime, here are some recent generationsshow more

This monkey is in an NIH laboratory run by... experimenter Elisabeth Murray. Murray subjects sensitive, vulnerable monkeys to procedures in which she saws open her victims’ skulls and injects toxins to burn brain cells, or suctions out parts of their brain to induce permanent damage. After sewing them back up, she places them in a small cage and deliberately provokes them with their worst fears, spiders and snakes, just to see how they’ll react. Although artificial, some of these realistic-looking spiders and snakes can move or even jump. She keeps monkeys hungry and thirsty to force them to cooperate, restrains them for extended periods of time, and implants head posts directly into their skulls. Some monkeys have lived for decades in her lab, pulling out their own hair and suffering with chronic diarrhea from the constant stress of living in a metal box. After these cruel and pointless experiments, Murray kills the monkeys. Murray’s experiments are an atrocity against monkeys and embarrassment to science. Text FRIGHT to 73822 to urge the NIH to end these experiments! *Message and data rates may apply. U.S. only. Text STOP to end and HELP for info. Periodic messaging. Full terms are available at:show more

Did you know we are having a Father’s Day... Sale? Shop the best-selling wallet of all time and choose from over 30+ colors and styles. Get UP TO 40% OFF👇show more