Knowledge catalogue
separating artifacts from the agent makes sense for sharing and cross-AI collaboration No vendor lock-in for your artifacts. Sites, decks, 3D games, reports, dashboards and galleries. Artifacts on Fly
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
this is what i'm talking about! https://x.com/sciencegirl/status/2109693723953000631?s=20 Researchers have taught a robotic hand to move independently. By treating its fingers as legs, AI learns to co
AI solved open mathematical problems. But the biggest surprise came afterwards. A team at Google DeepMind has used AI to resolve 9 open Erdős problems, including questions that had remained unsolved f
Introducing Anatomy Describe a machine in one line. Claude brings it to life. - Interactive isometric wireframes you can rotate, inspect and explore - WebGL shaders for fire, water, plasma and more -
Had fun nerding out on the @_odsc AI podcast about: • Building in public as both market diligence and a way to meet founders • Jev experiments: knowledge graphs, relevance filters, and emotional blobs
Btw, we're hiring. We're hiring the best engineers in the world. You're ambitious. Want to make something different. You learn and build fast. Our company is growing fast, so you need to grow even fas
i was told we can't fundraise and grow at the same time. it turned out we grew monthly usage 400% during fundraising. we have never run this fast. while taking 60 investor calls a week, we shipped 20
Introducing: Personal Agent Protocol (PAP)—an open standard for how personal agents interact with businesses. @stripe is joining Meta, Sierra, Genesys, Instinct, Rocket, Shopify, and Walmart as foundi
We just raised $7.7M to kill every subscription for agents. Introducing http://monid.ai, the openrouter for agent tools. Your agents can now: > discover, run, and pay for tools at runtime > use 2,500
if you’re building an ai app, you might want to host inference to improve your margins, and if you do that you should support a few models, and if you’re doing that you might as well build a router, a
😂 you might call this ... slippery slop if you’re building an ai app, you might want to host inference to improve your margins, and if you do that you should support a few models, and if you’re doing
On October 3, 2026 Yohei Nakajima posted a brief tweet praising the use of multiple AI coding assistants—Codex, Claude, Gemini, and Grok Bot—with a musical note emoji. The message also contains a Java
a lot of robot video data for thee We’re making the egocentric internet searchable. VideoDB now lets you search 12M+ task episodes from every open datasets. Type “arms folding a towel” and get thousan
Introducing MCP Sharing, built into FlyMyAI infra. Configure FlyMy MCP once: 1500+ MCPs inside, from Telegram and Slack to Instagram and Brex. Use it from Claude, Codex or any agent. Share it with you
who's got two thumbs and just ranked #6 of 49 on image-jevbench? 👍 this guy 👍 one of the fastest in top 10, accuracy is close. calibration of confidence is where it's weakest. @airesearch12 says a sim
i don’t get it fully but this looks cool We achieved a breakthrough at BTL. AI models are very linear. They think in one direction at a time, and when they're wrong they scramble and start again. For
This is exactly what I needed — running glance-qwen3-vl-4b locally on 2x RTX 3080 Ti to filter Pinterest pins at scale (text-overlay / usable / relevant, 3 questions per image).~220ms compute 😎😻 Media
btw i had no idea what i was doing when i started this but learned so much about models in the process and feel like i have a much better sense of what’s happening under the hood managing someone (an
glance-vlm speedlab is now open source! read: https://glance.yohei.me/speed/ try: https://github.com/yoheinakajima/glance-speedlab turn any webcam into multiple live AI detectors (emotion, count, obje
Introducing Contrastive Language Model (CLM): an ultra-fast System One Model trained with a contrastive learning objective that connects states and actions. CLM-8B is pre-trained on internet-scale dat
MiMo-V2.6-Pro is live on Wally. Day 1. @XiaomiMiMo's new open-weights flagship, top of the @ArtificialAnlys Intelligence Index for open-weight models. 320 tok/s, 2.4x the model maker's own API, in <24
New paper! 🫡 We introduce Matryoshka Attribution, a new attribution method which uses gradient descent to find which parts of a neural network are responsible for a behaviour. MAttr is #1 on the Mecha
“Hot dog or not?” at 0.4 sec 🌭 jev-style decision model for image [glance-qwen3-vl-4b] now on huggingface and replicate: Demo: https://glancevlm.replit.app Replicate: https://replicate.com/untapped/gl
now on replicate: “Hot dog or not?” at 0.4 sec 🌭 jev-style decision model for image [glance-qwen3-vl-4b] now on huggingface and replicate: Demo: https://glancevlm.replit.app Replicate: https://replica
On September 21 2026, Yohei reported results from a hard “insect‑identification” benchmark where model accuracy spanned 23 points across the evaluated systems. The Qwen 4B + Glance model scored 0.96,
Jev-style logit read on a 4B open VLM, measured: http://glance.yohei.me 👀 vs the same model writing JSON: ⏳ ~1/3 less time for a yes/no on a full photo 🤑 up to ~85% less GPU cost with many Qs per imag
Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepS
where it stops: geometry. relative size 0.52, diagonal direction 0.65, while GPT-5.6 and Gemini 3.1 Pro get 100%. UI screens: finding what to click is ~100% for everyone, one step of reasoning 0.90 vs
I've seen people describe Jev as an 'AI if statement'. But what if it actually WAS an if statement? Introducing Probably: a programming language powered by Jev: https://probably-lang.southpolesteve.wo
Epoch AI has launched “Benchmark Reviews,” an initiative to evaluate existing AI benchmark datasets. The program initially audits 15 benchmarks, categorizing them as 4 verified, 9 flawed, and 2 lackin
My name is Chris Painter, and I'm the President of METR (Model Evaluation and Threat Research). I know we've made a lot of new friends on the internet the last couple of days, so I thought I'd take th
the design of http://evaluatorbench.com grew out of a summer project, http://epistemedia.org (which i still need to write about), and runs on @activegraphai the pattern across all three projects is th
the independence of AI evaluators is going to matter more... so i made it a 'benchmark': http://evaluatorbench.com (research preview) source-linked directory of third-party evaluators of frontier AI.
Introducing our first agent tool: the Brand API This helps gen AI agents solve 3 problems: - Extract: produce on-brand assets when users already have a brand - Search: find and retrieve brands for ins
also this… not surprising cuz they have best distribution to normies, and i think agent quality is finally ready for them (e.g. you can connect things without ever seeing the word “MCP”) Muse is alrea
I have conducted an audit of Anthropic's finances. What I have found is so shocking that I am calling for a Congressional investigation. Anthropic is not just seeking regulatory capture. It has built
OK, let me irritate everyone for a moment ... The non cynical view here is that the labs are trying to navigate impending, unsophisticated federal regulation and a 'high strung', well financed doomer
// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear
CancerBench: the frontier model cancer cure benchmark. AI lab CEOs keep talking about curing cancer, so I made a benchmark. One metric: how many types of cancer has your model cured? All models are cu
i just tried Muse*, connected it to my GitHub, and continued the work I was doing in ChatGPT/Claude w no interruptions which is great cuz i now have more credits across more services to do work with :
Been posting individual pieces of RunAnywhere for months. Here's the whole thing in one place. RunAnywhere SDKs is a complete inference suite for any dev who wants to run AI on the user's device. ->8
so does this digital fly have the memory of the real fly that was scanned or what I’ve successfully run the full retained MaleCNS v1.0 fruit fly connectome, all 166,700 neurons, inside Minecraft, with
Paper Instruments benchmarked sandbox providers for their RL rollouts, and E2B's tool execution came in up to 3x faster than every other sandbox provider they tested, reducing idle GPU time and traini
[new @activegraphai blog post] How Synthetic Players used ActiveGraph to verify 4,919 runs without new model calls https://activegraph.ai/blog/synthetic-players-activegraph-replay For the increasing n
Today, Transluce is releasing the most expansive independent evaluation to date of how AI systems respond to users experiencing mental health crises. We evaluated 77 model variants from OpenAI, Anthro
One time, a young ML researcher asked Master Ilya: 'Teacher, according to the formulas, if I use the same seed and same prompt with the same weights, I will get the same results. Is my math right?' Ma
From the @HamsterResearch lab: Introducing Qwen3.8-Flash-Next-REAP-288-MLX-4bit, a 180B-class model running on just 39gb of memory - MLX-native 4-bit 60% smaller than stock q4 - Pruned 512→288 experts
Most companies manage their org chart, their product line, their brand guidelines, their operations manual. Each as a separate document. Each updated on its own cadence. Each a snapshot of a different
Today, we're kicking off the first phase of the research preview for Model Hardware Standard (MHS): a new standard for AI agents to safely operate physical equipment in scientific research and advance
are you ready to give your agent access to your bank account? AI agents need access to bank accounts and wallets with money in them. That's usually yours. We made it safe to give them access. Today we
get the most out of your agent traces w @agnostai Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-******
oooooh fancy new site? @shubhamintech Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Traine
Qwen 3.8 27B now runs locally inside RunAnywhere! Your app can use the same local AI setup across different hardware. On Mac it runs Swift + mlx. On Windows, Electron + llama.cpp. Different architectu
Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Trained for our first customer on their exis
this is going to expose a lot of bad products Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.
agent readiness check Want to see how a *real world* agent experiences your product? Use AgentJourney (for free!) to run any intent on any website. See its real-time journey, token usage, price - and
a very modular harness 👌 🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT lic
Has anyone built an app that sends you a notification to your phone? That's all I need, an app that connects to a cheap VPS and allows AI agents to send me notifications, so I can install a quick skil
Compression and LLMs are trying to solve the exact same problem: predicting what comes next. @_anniebabannie_'s interactive essay walks us through the basics of compression to reveal its surprising ov