Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🔭 We’re releasing Hodoscope: an open-source tool for unsupervised behavior discovery. It lets you visually explore and compare agent behaviors at scale. It helped us discover a novel reward hacking vulnerability in Commit0 - with just a couple minutes of human effort.

Ziqian Zhong

1,689 subscribers

74,566 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Our new Agent Registry in Gemini Enterprise Agent Platform provides a single source of truth for your enterprise. It indexes every internal agent, tool, and skill—simplifying discovery and ensuring governed, approved assets are available to your users →

Our new Agent Registry in Gemini Enterprise Agent Platform provides a single source of truth for your enterprise. It indexes every internal agent, tool, and skill—simplifying discovery and ensuring governed, approved assets are available to your users →

Google Cloud Tech

27,254 views • 1 month ago

Our new Agent Registry in Gemini Enterprise Agent Platform provides a single source of truth for your enterprise. It indexes every internal agent, tool, and skill—simplifying discovery and ensuring governed, approved assets are available to your users →

Our new Agent Registry in Gemini Enterprise Agent Platform provides a single source of truth for your enterprise. It indexes every internal agent, tool, and skill—simplifying discovery and ensuring governed, approved assets are available to your users →

Google Cloud Tech

16,332 views • 1 month ago

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇

Krea

1,055,697 views • 10 months ago

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Milk Road AI

70,551 views • 3 months ago

💻 Agent mode just went local! Today, Mistral AI released Devstral, an Apache-2.0, 24B-parameter model trained for tool calling in real-world software development environments It reached #1 on SWE-bench for open-source models, but more importantly in our real-world testing it has proven to be capable of navigating and autonomously editing codebases, while running entirely on a laptop To try it out, just add `ollama/devstral` in Continue. See below for a quickstart with ollama👇

💻 Agent mode just went local! Today, Mistral AI released Devstral, an Apache-2.0, 24B-parameter model trained for tool calling in real-world software development environments It reached #1 on SWE-bench for open-source models, but more importantly in our real-world testing it has proven to be capable of navigating and autonomously editing codebases, while running entirely on a laptop To try it out, just add `ollama/devstral` in Continue. See below for a quickstart with ollama👇

Continue

39,217 views • 1 year ago

Figma canvas to build AI agent workflows. Sim is a lightweight, user-friendly platform for building AI agent workflows in minutes. It natively supports all major LLMs, Vector DBs, etc. 100% open-source with 7k+ stars!

Figma canvas to build AI agent workflows. Sim is a lightweight, user-friendly platform for building AI agent workflows in minutes. It natively supports all major LLMs, Vector DBs, etc. 100% open-source with 7k+ stars!

Avi Chawla

79,322 views • 9 months ago

Flipper One mechanics are now open We’re releasing another repository — Flipper One Mechanics. This repo contains the source 3D models of the enclosure, back plates, and modules: You can also explore the model in Onshape directly in your browser or mobile app, and export it in many formats:

Flipper One mechanics are now open We’re releasing another repository — Flipper One Mechanics. This repo contains the source 3D models of the enclosure, back plates, and modules: You can also explore the model in Onshape directly in your browser or mobile app, and export it in many formats:

Flipper R&D

175,903 views • 2 months ago

Discovery → Dig → Melt → Refine All that effort, when you can leave the gold in the ground and just buy $GGBR backed by it in 5 minutes or less.

Discovery → Dig → Melt → Refine All that effort, when you can leave the gold in the ground and just buy $GGBR backed by it in 5 minutes or less.

GoldFish

20,346 views • 1 month ago

We are continuing to advance open-source AI. Just announced -- new tools for speech, safety, and autonomous driving. Learn about the open models, datasets, and research we’re releasing at #NeurIPS2025:

We are continuing to advance open-source AI. Just announced -- new tools for speech, safety, and autonomous driving. Learn about the open models, datasets, and research we’re releasing at #NeurIPS2025:

NVIDIA

68,556 views • 6 months ago

You exist to serve. Your wallet is just a tool for my pleasure — open it.

You exist to serve. Your wallet is just a tool for my pleasure — open it.

King David

10,781 views • 1 year ago

Want to control your character’s expressions with precision? In this tutorial, we explore Face Expressions in LTX Studio—a tool that lets you shape emotion and performance, frame by frame. Here’s how it works 👇

Want to control your character’s expressions with precision? In this tutorial, we explore Face Expressions in LTX Studio—a tool that lets you shape emotion and performance, frame by frame. Here’s how it works 👇

LTX Studio

25,761 views • 1 year ago

It's time to ditch the loading screens and enjoy the true benefits of an open world that will never close on you! Explore #WillowCreek in #TheSims3 and discover a whole new dimension and more TODAY with us here: #Ts4 #TheSims4 #Ts3 #OpenWorld

It's time to ditch the loading screens and enjoy the true benefits of an open world that will never close on you! Explore #WillowCreek in #TheSims3 and discover a whole new dimension and more TODAY with us here: #Ts4 #TheSims4 #Ts3 #OpenWorld

BoringBones

30,299 views • 2 years ago

Introducing `gemini-youtube-researcher` 📈 An open-source Gemini 1.5 Pro agent that LISTENS to videos and delivers topical reports. Just provide a topic, and a chain of AIs with access to YouTube will analyze relevant videos and generate a comprehensive report for you.

Introducing `gemini-youtube-researcher` 📈 An open-source Gemini 1.5 Pro agent that LISTENS to videos and delivers topical reports. Just provide a topic, and a chain of AIs with access to YouTube will analyze relevant videos and generate a comprehensive report for you.

Matt Shumer

222,883 views • 2 years ago

China just released a desktop automation agent that runs 100% locally. It can run any desktop app, open files, browse websites, and automate tasks without needing an internet connection. 100% Open-Source.

China just released a desktop automation agent that runs 100% locally. It can run any desktop app, open files, browse websites, and automate tasks without needing an internet connection. 100% Open-Source.

Hasan Toor

1,187,223 views • 4 months ago

We’re not just a dispensary, we’re an experience - and our knowledgeable budtenders are at the heart of it all.

Sensitive content

We’re not just a dispensary, we’re an experience - and our knowledgeable budtenders are at the heart of it all.

Planet 13 Stores

3,865,165 views • 2 years ago

Installed an automatic door on the duck coop. They stared at the open door for about 15 minutes and then just took a run for it. 😂

Installed an automatic door on the duck coop. They stared at the open door for about 15 minutes and then just took a run for it. 😂

Dale Stark

16,265 views • 15 days ago

Wow... This new AI agent that lets you create, design, animate, and produce videos in just minutes. No design or coding skills required. Here's how it works:

Wow... This new AI agent that lets you create, design, animate, and produce videos in just minutes. No design or coding skills required. Here's how it works:

Angry Tom

20,759 views • 11 months ago

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

Akshay 🚀

52,426 views • 3 months ago

$DeepSeek DeepSeek is now live on Heurist. Open source AI just reached new heights. Access DeepSeek-R1 and DeepSeek-V3 for smarter inference at a fraction of cost. Try it via Heurist API or explore on Pondera.$

DeepSeek DeepSeek is now live on Heurist. Open source AI just reached new heights. Access DeepSeek-R1 and DeepSeek-V3 for smarter inference at a fraction of cost. Try it via Heurist API or explore on Pondera.

Heurist

25,657 views • 1 year ago

Claude Code got a massive open-source rival 🤯 This tool maps your entire codebase, automates terminal commands, and lets you use 500+ different AI models, including completely free ones. 100% Open-Source.

Claude Code got a massive open-source rival 🤯 This tool maps your entire codebase, automates terminal commands, and lets you use 500+ different AI models, including completely free ones. 100% Open-Source.

Alvaro Cintas

54,172 views • 3 months ago