Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🔭 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.

fjzzq2002's profile picture

Ziqian Zhong ✈️ COLM 2026

2,476 subscribers

76,928 Aufrufe • vor 8 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche 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 →
0:19

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

16,419 Aufrufe • vor 6 Monaten

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 →
0:10

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 Aufrufe • vor 5 Monaten

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 👇
0:19

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

1,055,965 Aufrufe • vor 1 Jahr

THIS IS WHAT A SUPPORT TEAM LOOKS LIKE IN 2026 A customer reports that their export stops at 10,000 of 18,400 contacts. And instead of passing the ticket from tool to tool: → Support agent replies → Coding agent finds the bug → Docs agent updates the guide → CRM agent prepares the renewal All on the same ticket, with the same context: logs, billing, code and previous conversations. It's called Helpin. It's open source and you can self-host it.
0:15

THIS IS WHAT A SUPPORT TEAM LOOKS LIKE IN 2026 A customer reports that their export stops at 10,000 of 18,400 contacts. And instead of passing the ticket from tool to tool: → Support agent replies → Coding agent finds the bug → Docs agent updates the guide → CRM agent prepares the renewal All on the same ticket, with the same context: logs, billing, code and previous conversations. It's called Helpin. It's open source and you can self-host it.

marcus

22,919 Aufrufe • vor 25 Tagen

Introducing Pages on Superset mobile Your agents can now deliver interactive demos, mockups, and reports as Pages you can review from your phone. Ask an agent to build a feature, compare designs, or investigate a problem. It can put the result in a Page with the context you need to review it and give feedback. A few ways to use it: • Feature work: try an interactive demo, then inspect the code in the PR. • Design reviews: compare mockups and before-and-after screenshots. • Investigations: explore findings, charts, and recommendations in one place. To try it, ask your agent to build a feature and create a Page for you to review.
0:17

Introducing Pages on Superset mobile Your agents can now deliver interactive demos, mockups, and reports as Pages you can review from your phone. Ask an agent to build a feature, compare designs, or investigate a problem. It can put the result in a Page with the context you need to review it and give feedback. A few ways to use it: • Feature work: try an interactive demo, then inspect the code in the PR. • Design reviews: compare mockups and before-and-after screenshots. • Investigations: explore findings, charts, and recommendations in one place. To try it, ask your agent to build a feature and create a Page for you to review.

Kiet

85,841 Aufrufe • vor 1 Monat

new skill: create-canvas. last week I made a skill to put every component from a repo on one canvas. I started using it with my agent to create variations, compare ideas, and iterate visually without leaving the codebase. so I made a new skill around that workflow. instead of moving your work into another tool, bring the canvas into your codebase and use it to explore UI with your agent, using the real components, styles, and project context already there.
0:10

new skill: create-canvas. last week I made a skill to put every component from a repo on one canvas. I started using it with my agent to create variations, compare ideas, and iterate visually without leaving the codebase. so I made a new skill around that workflow. instead of moving your work into another tool, bring the canvas into your codebase and use it to explore UI with your agent, using the real components, styles, and project context already there.

Ibelick

39,091 Aufrufe • vor 13 Tagen

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:
0:13

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

Sergio Paniego

38,088 Aufrufe • vor 2 Monaten

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.
0:15

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

70,655 Aufrufe • vor 7 Monaten

Check out this robot hexapod with a 25Kg payload that can run for an hour on a single power tool battery. It is fully open source and runs #ROS Jazzy.
0:12

Check out this robot hexapod with a 25Kg payload that can run for an hour on a single power tool battery. It is fully open source and runs #ROS Jazzy.

Open Robotics

12,060 Aufrufe • vor 3 Monaten

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:
0:19

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

179,138 Aufrufe • vor 7 Monaten

Something just launched that makes VS Code feel ancient. And im all in for it: Cline Desktop app, an open-source app for open-weight models (and you know how much i love open source) brings its coding agent into a standalone Cline Desktop app for Mac + Windows. Just open a project and tell it what you want to change. No need to open VS Code first. In Cline's demo, it adds priority filters to a task board, works through the code and runs the build. Glad to see the model choice stays open, too. You can bring your own API keys, use supported open-weight models and even switch models halfway through a project!
0:17

Something just launched that makes VS Code feel ancient. And im all in for it: Cline Desktop app, an open-source app for open-weight models (and you know how much i love open source) brings its coding agent into a standalone Cline Desktop app for Mac + Windows. Just open a project and tell it what you want to change. No need to open VS Code first. In Cline's demo, it adds priority filters to a task board, works through the code and runs the build. Glad to see the model choice stays open, too. You can bring your own API keys, use supported open-weight models and even switch models halfway through a project!

Chubby♨️

40,292 Aufrufe • vor 1 Monat

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.
0:13

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

21,761 Aufrufe • vor 5 Monaten

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:
0:10

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

69,061 Aufrufe • vor 11 Monaten

You can now use Figma for FREE with this tool. It's called Penpot. An open-source design tool that mirrors Figma's layout and workflow, free, self-hostable → MCP server lets AI agents edit your designs directly → Free Dev Mode with instant CSS, SVG, and HTML → Native design tokens keep design & code in sync → Real-time collaboration built in 100% Free. Open source.
0:13

You can now use Figma for FREE with this tool. It's called Penpot. An open-source design tool that mirrors Figma's layout and workflow, free, self-hostable → MCP server lets AI agents edit your designs directly → Free Dev Mode with instant CSS, SVG, and HTML → Native design tokens keep design & code in sync → Real-time collaboration built in 100% Free. Open source.

Simplifying AI

57,450 Aufrufe • vor 3 Monaten

THIS IS F**KING DANGEROUS THREE OPEN SOURCE AI CYBERSECURITY STACK MOST PEOPLE DONT KNOW EXISTS METATRON: point it at a target, it recon's, analyzes, and reports on its own —> fully OFFLINE , zero API keys. NUCLEI : describe a vulnerability in plain English, it writes and runs the actual detection template for you. GARAK BY (NVIDIA): throws thousands of known prompt injection and jailbreak attempts at an LLM until one breaks through. Recon —> detection —> and AI red teaming three layers of the same problem, all open source. Link to access the REPO’S below
0:19

THIS IS F**KING DANGEROUS THREE OPEN SOURCE AI CYBERSECURITY STACK MOST PEOPLE DONT KNOW EXISTS METATRON: point it at a target, it recon's, analyzes, and reports on its own —> fully OFFLINE , zero API keys. NUCLEI : describe a vulnerability in plain English, it writes and runs the actual detection template for you. GARAK BY (NVIDIA): throws thousands of known prompt injection and jailbreak attempts at an LLM until one breaks through. Recon —> detection —> and AI red teaming three layers of the same problem, all open source. Link to access the REPO’S below

MAX

107,500 Aufrufe • vor 2 Monaten

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
0:16

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 Aufrufe • vor 3 Jahren

UI/UX Designers, you can now render and animate 3D models without opening Blender. I just found this amazing tool called Morflax, a simple browser-based tool that lets you upload a 3D model, customize materials and lighting, and export stunning video animations in minutes. Can’t believe it’s free; bookmark it for later. 💜
0:16

UI/UX Designers, you can now render and animate 3D models without opening Blender. I just found this amazing tool called Morflax, a simple browser-based tool that lets you upload a 3D model, customize materials and lighting, and export stunning video animations in minutes. Can’t believe it’s free; bookmark it for later. 💜

Abraham John 🦄🦓

17,866 Aufrufe • vor 4 Monaten

SOMEONE JUST BUILT A FREE OPEN-SOURCE TOOL THAT TURNS GPT-6 ASTRA OR ANY AI MODEL INTO A WORKFLOW BOT. IT RUNS LOCALLY, SUPPORTS 1,200 INTEGRATIONS AND PUTS A HUMAN APPROVAL GATE BEFORE EVERY EXTERNAL ACTION.
0:18

SOMEONE JUST BUILT A FREE OPEN-SOURCE TOOL THAT TURNS GPT-6 ASTRA OR ANY AI MODEL INTO A WORKFLOW BOT. IT RUNS LOCALLY, SUPPORTS 1,200 INTEGRATIONS AND PUTS A HUMAN APPROVAL GATE BEFORE EVERY EXTERNAL ACTION.

0xMarioNawfal

52,128 Aufrufe • vor 1 Monat