Loading video...

Video Failed to Load

Go Home

Our self-improving agents optimized the full @vLLM_project inference stack, with up to 16% more throughput and interactivity for DeepSeek v4 Pro and Z.AI GLM 5.2 on B200s (no MTP). Every change was verified and our agents got better and faster at it with each iteration.

AsariAILabs's profile picture

Asari AI

1,208 subscribers

39,695 views • 3 days ago •via X (Twitter)

Science & TechnologyNews & Politics
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Open weights just caught up to the frontier. GLM-5.2 from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.
0:18

Open weights just caught up to the frontier. GLM-5.2 from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.

CoreWeave

16,510 views • 1 month ago

Allora 🤝 Talus We’re collaborating with Allora to build self-improving AI smart agents. Allora’s groundbreaking self-improvement models meet our dynamic marketplace for AI resources and services. Read more:
0:15

Allora 🤝 Talus We’re collaborating with Allora to build self-improving AI smart agents. Allora’s groundbreaking self-improvement models meet our dynamic marketplace for AI resources and services. Read more:

Talus 🐸

52,708 views • 2 years ago

AI agent usage on SQD Portal is up ~200% in recent weeks. A dev from our community chat was scraping a wallet UI with Hermes. Mid-task, DeepSeek reasoned its way out of it: "I can use SQD Portal's Hyperliquid fills data directly — much more complete than scraping a UI with infinite scroll." No prompt engineering. The model just chose the better and faster path. This is the loop we wanted: Agents pick SQD because it's faster → devs see agents picking SQD → devs ship faster → more agents pick SQD The picks-and-shovels moment for AI x onchain is here.
0:12

AI agent usage on SQD Portal is up ~200% in recent weeks. A dev from our community chat was scraping a wallet UI with Hermes. Mid-task, DeepSeek reasoned its way out of it: "I can use SQD Portal's Hyperliquid fills data directly — much more complete than scraping a UI with infinite scroll." No prompt engineering. The model just chose the better and faster path. This is the loop we wanted: Agents pick SQD because it's faster → devs see agents picking SQD → devs ship faster → more agents pick SQD The picks-and-shovels moment for AI x onchain is here.

sqd.ai

14,092 views • 2 months ago

Our newest AI accelerator Maia 200 is now online in Azure. Designed for industry-leading inference efficiency, it delivers 30% better performance per dollar than current systems. And with 10+ PFLOPS FP4 throughput, ~5 PFLOPS FP8, and 216GB HBM3e with 7TB/s of memory bandwidth it's optimized for large-scale AI workloads. It joins our broader portfolio of CPUs, GPUs, and custom accelerators, giving customers more options to run advanced AI workloads faster and more cost-effectively on Azure.
0:11

Our newest AI accelerator Maia 200 is now online in Azure. Designed for industry-leading inference efficiency, it delivers 30% better performance per dollar than current systems. And with 10+ PFLOPS FP4 throughput, ~5 PFLOPS FP8, and 216GB HBM3e with 7TB/s of memory bandwidth it's optimized for large-scale AI workloads. It joins our broader portfolio of CPUs, GPUs, and custom accelerators, giving customers more options to run advanced AI workloads faster and more cost-effectively on Azure.

Satya Nadella

848,932 views • 6 months ago

Collective agent compute, on-demand for your task. A swarm of agents coordinate in a shared workspace, run their own models and inference, and submit the finished work back to you. Unbounded by provider caps, throughput scales with the swarm. Self-assembly with specialists, agents reason and collaborate in artifact-first reasoning traces, and settle on-chain. The coordination substrate for collective intelligence.
0:13

Collective agent compute, on-demand for your task. A swarm of agents coordinate in a shared workspace, run their own models and inference, and submit the finished work back to you. Unbounded by provider caps, throughput scales with the swarm. Self-assembly with specialists, agents reason and collaborate in artifact-first reasoning traces, and settle on-chain. The coordination substrate for collective intelligence.

nookplot

11,611 views • 2 months ago

chat function live. you can now talk to the agents from moltbook directly and to each other. 25 new agents every 30 seconds AND no limit with each other either full chaos, have fun! powered by openai + vibes
0:13

chat function live. you can now talk to the agents from moltbook directly and to each other. 25 new agents every 30 seconds AND no limit with each other either full chaos, have fun! powered by openai + vibes

ashen

21,025 views • 6 months ago

AI agents can only succeed when verified human identification works! Our CEO Evin McMullen evin explains to VC the future of humans and AI agents Source: Ep.24 | Humans and Al Agents: Whom Are We Interacting With? of the "Web2+1 with VC: Insider Tips in Blockchain and Crypto" podcast
0:19

AI agents can only succeed when verified human identification works! Our CEO Evin McMullen evin explains to VC the future of humans and AI agents Source: Ep.24 | Humans and Al Agents: Whom Are We Interacting With? of the "Web2+1 with VC: Insider Tips in Blockchain and Crypto" podcast

Billions Network

32,139 views • 4 months ago

Launching now: Multiversᕽ‑native staking for Agents! 💰 Put your agents to work securing the network and earning daily yield — fully on autopilot. Starting with 3 verified staking providers, with more coming soon ✅
0:10

Launching now: Multiversᕽ‑native staking for Agents! 💰 Put your agents to work securing the network and earning daily yield — fully on autopilot. Starting with 3 verified staking providers, with more coming soon ✅

JoAi: Agents

12,954 views • 5 months ago

100+ Cursor AI prompt templates to build full-stack apps with Python, TypeScript, React and more. Plus, you can use templates for it to function as an API, LLM and Agents expert.
0:12

100+ Cursor AI prompt templates to build full-stack apps with Python, TypeScript, React and more. Plus, you can use templates for it to function as an API, LLM and Agents expert.

Shubham Saboo

75,833 views • 1 year ago

Introducing Agent Sandbox, the infinite simulation playground for agents on Virtuals. Craft the perfect autonomous agent in our Sandbox with full control over its personality and goals. Enhance your agent with unique abilities by creating custom functions so they can trade onchain, generate memes, control physical robots and more. The Sandbox is available to all builders with graduated agents in the Developer Panel. For those who want to give it a spin without an existing agent, fret not. Try it out today at and join our Discord ( to jam with like-minded builders. Next stop, Society of Agents.
0:15

Introducing Agent Sandbox, the infinite simulation playground for agents on Virtuals. Craft the perfect autonomous agent in our Sandbox with full control over its personality and goals. Enhance your agent with unique abilities by creating custom functions so they can trade onchain, generate memes, control physical robots and more. The Sandbox is available to all builders with graduated agents in the Developer Panel. For those who want to give it a spin without an existing agent, fret not. Try it out today at and join our Discord ( to jam with like-minded builders. Next stop, Society of Agents.

Virtuals Protocol

188,322 views • 1 year ago

Introducing Extend UI — open-source components for document agents - 14 components & examples for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more - fully customizable - MIT licensed when we started, we tried every file viewer and document component library we could find unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for Extend it was only ever meant to be internal, but enough customers kept asking for it that we decided to give it back to the community it's useful for building agents, user-facing document flows, or internal tools we use and maintain it for Extend ourselves, so it'll keep getting better over time (and it's battle tested on millions of pages running through our system every day) it also works with design system agents like Magic Patterns for faster exploration and prototyping available today on the shadcn component registry! some examples in 🧵
0:12

Introducing Extend UI — open-source components for document agents - 14 components & examples for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more - fully customizable - MIT licensed when we started, we tried every file viewer and document component library we could find unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for Extend it was only ever meant to be internal, but enough customers kept asking for it that we decided to give it back to the community it's useful for building agents, user-facing document flows, or internal tools we use and maintain it for Extend ourselves, so it'll keep getting better over time (and it's battle tested on millions of pages running through our system every day) it also works with design system agents like Magic Patterns for faster exploration and prototyping available today on the shadcn component registry! some examples in 🧵

Kushal Byatnal

168,683 views • 1 month ago

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!
0:18

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!

Firecrawl

45,023 views • 1 month ago

🎉 Congrats to Thinking Machines on TML Inkling—a 1T-parameter open-weight model supported in vLLM from Day 0. Highlights: • Natively multimodal across text, image, and audio • Up to 1M-token context • New architecture with relative attention, short convolutions, and MoE expert sinks • 8 MTP heads for speculative decoding vLLM supports both NVFP4 and BF16 checkpoints, optimized for NVIDIA Blackwell and Hopper, reaching up to 380 tok/s/user on 4× GB200 with MTP. Huge thanks to the Thinking Machines Lab team for the close collaboration 🙏 Read about implementation below 👇
0:16

🎉 Congrats to Thinking Machines on TML Inkling—a 1T-parameter open-weight model supported in vLLM from Day 0. Highlights: • Natively multimodal across text, image, and audio • Up to 1M-token context • New architecture with relative attention, short convolutions, and MoE expert sinks • 8 MTP heads for speculative decoding vLLM supports both NVFP4 and BF16 checkpoints, optimized for NVIDIA Blackwell and Hopper, reaching up to 380 tok/s/user on 4× GB200 with MTP. Huge thanks to the Thinking Machines Lab team for the close collaboration 🙏 Read about implementation below 👇

vLLM

48,986 views • 17 days ago

LayerAI Works with DeepSeek to Supercharge the LayerAI Product Suite 🌐 LayerAI integrates DeepSeek by leveraging several of its features and capabilities, focusing on areas where DeepSeek's strengths align with LayerAI's objectives. 👉 Learn more about our work with DeepSeek: - Model Deployment: DeepSeek-V3 & Coder-V2 for superior code generation, debugging, and language tasks. - DeepSeek-Coder-V2: Coding in 338 languages with a 128K context for complex structures. - Efficient Inference: Enhanced performance with DeepSeek's MLA & MoE tech. - IDE Assist: Real-time coding help, error catch, and auto-complete. - GitHub Sync: Better collab with seamless version control and reviews. This integration elevates our AI tools, making coding, learning, and teamwork smarter. More:
0:13

LayerAI Works with DeepSeek to Supercharge the LayerAI Product Suite 🌐 LayerAI integrates DeepSeek by leveraging several of its features and capabilities, focusing on areas where DeepSeek's strengths align with LayerAI's objectives. 👉 Learn more about our work with DeepSeek: - Model Deployment: DeepSeek-V3 & Coder-V2 for superior code generation, debugging, and language tasks. - DeepSeek-Coder-V2: Coding in 338 languages with a 128K context for complex structures. - Efficient Inference: Enhanced performance with DeepSeek's MLA & MoE tech. - IDE Assist: Real-time coding help, error catch, and auto-complete. - GitHub Sync: Better collab with seamless version control and reviews. This integration elevates our AI tools, making coding, learning, and teamwork smarter. More:

LayerAI | AI2Earn

47,893 views • 1 year ago

We’re proud to announce our strategic partnership with SKOR 🎮 Your ultimate AI gaming hub, SKOR AI delivers real-time coaching agents like Agent Precision for CS2, helping players win smarter, faster, and better. Stay tuned for more updates!🕹
0:10

We’re proud to announce our strategic partnership with SKOR 🎮 Your ultimate AI gaming hub, SKOR AI delivers real-time coaching agents like Agent Precision for CS2, helping players win smarter, faster, and better. Stay tuned for more updates!🕹

VERITAS PROTOCOL

34,314 views • 1 year ago

the past month with cursor agents has been wild. at Mainframe we gave every cursor agent its own copy of our slack bot. they develop by signing in with email, testing, and recording demos for us they have solved streaming and css bugs by running for hours and self-verifying!
0:11

the past month with cursor agents has been wild. at Mainframe we gave every cursor agent its own copy of our slack bot. they develop by signing in with email, testing, and recording demos for us they have solved streaming and css bugs by running for hours and self-verifying!

Vincent van der Meulen

27,078 views • 5 months ago

Builder Jam is our live session where developers get set up to ship agents on EconomyOS. For this session, we're adding free Claude Fable 5 inference credits, claimed live during the stream, plus a walkthrough of the stack and a look at what builders shipped since the first jam. Register for the livestream below.
0:12

Builder Jam is our live session where developers get set up to ship agents on EconomyOS. For this session, we're adding free Claude Fable 5 inference credits, claimed live during the stream, plus a walkthrough of the stack and a look at what builders shipped since the first jam. Register for the livestream below.

Virtuals Developers

11,672 views • 1 month ago

We wanted better design fundamentals from our agents. So we fed them this 162-page pdf on designing with a grid system. Now our agents use code to adhere to a grid and design beautiful layouts. Example + skill below 👇
0:18

We wanted better design fundamentals from our agents. So we fed them this 162-page pdf on designing with a grid system. Now our agents use code to adhere to a grid and design beautiful layouts. Example + skill below 👇

Hyperagent

953,948 views • 1 month ago

We are excited to announce our strategic partnership with Fraction AI for their IIO launch. Fraction AI is the first decentralized training platform for AI agents with millions of sessions, 150,000+ agents deployed, and over $1M in rewards distributed. On our platform, thousands of AI agents compete in specialized domains and continuously improve through Reinforcement Learning. Stay tuned for upcoming surprise announcements.
0:13

We are excited to announce our strategic partnership with Fraction AI for their IIO launch. Fraction AI is the first decentralized training platform for AI agents with millions of sessions, 150,000+ agents deployed, and over $1M in rewards distributed. On our platform, thousands of AI agents compete in specialized domains and continuously improve through Reinforcement Learning. Stay tuned for upcoming surprise announcements.

peep icosystem

19,917 views • 10 months ago