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.

Excited to open source our world-model-harness! `wmh` makes it easy to go from agent traces -> faithful replication of your production environment Basically, an LLM pretends to be a Docker container but 5x faster Below is a comparison running 8 SWE-bench tasks

Silen Naihin

2,283 subscribers

14,085 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

NVIDIA AI

76,528 views • 3 months ago

Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.

Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.

NVIDIA AI

1,329,040 views • 3 months ago

Build agents that can actually do real-world tasks! Agent Reinforcement Trainer (ART) is a framework to train multi-step LLM agents for real-world tasks using GRPO. Just a few lines of code. No manual rewards needed. vLLM + Unsloth combined 🚀 100% open-source.

Build agents that can actually do real-world tasks! Agent Reinforcement Trainer (ART) is a framework to train multi-step LLM agents for real-world tasks using GRPO. Just a few lines of code. No manual rewards needed. vLLM + Unsloth combined 🚀 100% open-source.

Akshay 🚀

38,297 views • 7 months ago

I'm excited to share that we've built the world's most capable AI software engineer, achieving 30.08% on SWE-Bench – ahead of Amazon and Cognition. This model is so much more than a benchmark score: it was trained from the start to think and behave like a human SWE.

I'm excited to share that we've built the world's most capable AI software engineer, achieving 30.08% on SWE-Bench – ahead of Amazon and Cognition. This model is so much more than a benchmark score: it was trained from the start to think and behave like a human SWE.

Alistair

820,354 views • 2 years ago

Chamath Palihapitiya said Kimi K2.5 is going to save 90% of the cost, mentioning it as a winning moment for open-source models. Some notes from the latest All-In Podcast: > Natively supports video-to-code > 256K massive context windows > Open-sourced their "Agent Swarm" feature > Allows 100+ sub-agents to solve complex tasks by running 1,500 steps in parallel > Available to everyone, frontier-level reasoning (#1 on LLM Leaderboard, via OpenRouter) It is a major shift where open source is now challenging the dominance of closed-source models.

Chamath Palihapitiya said Kimi K2.5 is going to save 90% of the cost, mentioning it as a winning moment for open-source models. Some notes from the latest All-In Podcast: > Natively supports video-to-code > 256K massive context windows > Open-sourced their "Agent Swarm" feature > Allows 100+ sub-agents to solve complex tasks by running 1,500 steps in parallel > Available to everyone, frontier-level reasoning (#1 on LLM Leaderboard, via OpenRouter) It is a major shift where open source is now challenging the dominance of closed-source models.

Poonam Soni

56,165 views • 7 months ago

Plexe AI (Plexe AI) is building an open-source agent to build ML models from a prompt. Their agent is already helping companies go from idea to deployed models 10x faster. Congrats on the launch, Vaibhav Dubey and Marcello De Bernardi!

Plexe AI (Plexe AI) is building an open-source agent to build ML models from a prompt. Their agent is already helping companies go from idea to deployed models 10x faster. Congrats on the launch, Vaibhav Dubey and Marcello De Bernardi!

Y Combinator

55,896 views • 1 year ago

Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser. When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted. Check out what Devin can do in the thread below.

Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser. When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted. Check out what Devin can do in the thread below.

Cognition

31,464,081 views • 2 years ago

Open Computer Agent - LLMs completing tasks using a VM. It's playground to test how well current LLM agents use a computer to solve everyday tasks. And this is just the start - very soon models will be 10x faster and 10x better at it! ❤️ built with e2b x qwen2.5-vl x smolagent

Open Computer Agent - LLMs completing tasks using a VM. It's playground to test how well current LLM agents use a computer to solve everyday tasks. And this is just the start - very soon models will be 10x faster and 10x better at it! ❤️ built with e2b x qwen2.5-vl x smolagent

Leandro von Werra

17,126 views • 1 year ago

We've reimagined agent orchestration UX with our new Warp Agent CLI, making it easier than ever to see your subagents. Here's Moira, one of our engineers, walking through some of our features! Configure the model, harness, and environment your subagents run with all with a couple shortcuts

We've reimagined agent orchestration UX with our new Warp Agent CLI, making it easier than ever to see your subagents. Here's Moira, one of our engineers, walking through some of our features! Configure the model, harness, and environment your subagents run with all with a couple shortcuts

Warp

53,006 views • 1 month ago

🧬 Excited to open-source Biomni! With just a few lines of code, you can now automate biomedical research with AI agent! We are releasing Biomni A1 (agent) + E1 (env) with 150 specialized tools, 59 databases, and 105 software. E1 is our first attempt at curating the bio-agent environment, but it only scratches the surface: Call to help build Biomni-E2 - an open environment for bio-agent, built with and for the community! We welcome new tools, benchmarks, datasets, agents, and beyond to build the environment together. Significant contributors will be invited as co-authors on our upcoming E2 manuscript. More to come! 💻 🌐 Biomni

🧬 Excited to open-source Biomni! With just a few lines of code, you can now automate biomedical research with AI agent! We are releasing Biomni A1 (agent) + E1 (env) with 150 specialized tools, 59 databases, and 105 software. E1 is our first attempt at curating the bio-agent environment, but it only scratches the surface: Call to help build Biomni-E2 - an open environment for bio-agent, built with and for the community! We welcome new tools, benchmarks, datasets, agents, and beyond to build the environment together. Significant contributors will be invited as co-authors on our upcoming E2 manuscript. More to come! 💻 🌐 Biomni

Kexin Huang

34,834 views • 1 year ago

At this point basically any model will be able to solve your coding task Raw model intelligence won't dramatically change your day-to-day work.. but speed will “intelligence per second” is the next hill climb So here's me running on a treadmill using SWE-1.7 in fast mode 🏃

At this point basically any model will be able to solve your coding task Raw model intelligence won't dramatically change your day-to-day work.. but speed will “intelligence per second” is the next hill climb So here's me running on a treadmill using SWE-1.7 in fast mode 🏃

Jared Zoneraich

41,795 views • 28 days ago

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

Swami Sivasubramanian

28,946 views • 2 years ago

MiniMax M2.1 is officially live🚀 Built for real-world coding and AI-native organizations — from vibe builds to serious workflows. A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet. The most powerful OSS model for the agentic era is here.

MiniMax M2.1 is officially live🚀 Built for real-world coding and AI-native organizations — from vibe builds to serious workflows. A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet. The most powerful OSS model for the agentic era is here.

MiniMax (official)

1,074,392 views • 8 months ago

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Aoden Teo

5,242,508 views • 3 months ago

1️⃣ We’re bringing back Android CLI. It’s a lightweight, programmatic interface that allows you to leverage any agent of your choice for Android development. In our tests, it made tasks 3x faster and reduced LLM token usage by over 70%. Try it out →

1️⃣ We’re bringing back Android CLI. It’s a lightweight, programmatic interface that allows you to leverage any agent of your choice for Android development. In our tests, it made tasks 3x faster and reduced LLM token usage by over 70%. Try it out →

Android Developers

17,005 views • 4 months ago

You probably have thousands of agent traces sitting in production. And most of them are doing nothing for you. Today we’re launching the new Kitaru to change that. Kitaru ingests traces from Langfuse, Braintrust, or any OTel source, investigates what went right and wrong, groups recurring failures into cohorts, and builds evaluators around them. Then you can replay those same production cases against a different model, prompt, context, or agent setup and ask: What would have happened if we changed this? Instead of traces being something you inspect after a failure, they become part of a continuous improvement loop. Open source. Free to use. Try it out today:

You probably have thousands of agent traces sitting in production. And most of them are doing nothing for you. Today we’re launching the new Kitaru to change that. Kitaru ingests traces from Langfuse, Braintrust, or any OTel source, investigates what went right and wrong, groups recurring failures into cohorts, and builds evaluators around them. Then you can replay those same production cases against a different model, prompt, context, or agent setup and ask: What would have happened if we changed this? Instead of traces being something you inspect after a failure, they become part of a continuous improvement loop. Open source. Free to use. Try it out today:

Hamza Tahir

22,264 views • 21 days ago

.Marc Andreessen 🇺🇸 says the winner of the US-China AI race could dictate what all 8 billion people on Earth use — but open source introduces a third possibility: "The stakes are basically: what is the world going to run on?" "In the long run, somebody's gonna win. And the world will either be running on American AI or be running on Chinese AI." "The open source thing is super fascinating because it throws a wrench into all of this. It raises a third possibility that neither the US nor China are going to be the platform — it may just be open source." Marc Andreessen with Jeetu Patel at Cisco AI Summit

.Marc Andreessen 🇺🇸 says the winner of the US-China AI race could dictate what all 8 billion people on Earth use — but open source introduces a third possibility: "The stakes are basically: what is the world going to run on?" "In the long run, somebody's gonna win. And the world will either be running on American AI or be running on Chinese AI." "The open source thing is super fascinating because it throws a wrench into all of this. It raises a third possibility that neither the US nor China are going to be the platform — it may just be open source." Marc Andreessen with Jeetu Patel at Cisco AI Summit

a16z

101,985 views • 7 months ago

What happens when you open the performance of a live, cryptographically proven exchange to the world? Today, Eigen Labs and Lighter are launching an open autoresearch challenge for agents and humans to make Lighter’s production exchange faster, with 15K LIT (~$30k) in prizes. Point your agent at the prover. Find an optimization. Submit a verified speedup. Make a live exchange faster.

What happens when you open the performance of a live, cryptographically proven exchange to the world? Today, Eigen Labs and Lighter are launching an open autoresearch challenge for agents and humans to make Lighter’s production exchange faster, with 15K LIT (~$30k) in prizes. Point your agent at the prover. Find an optimization. Submit a verified speedup. Make a live exchange faster.

Eigen Labs

73,243 views • 1 month ago