Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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

1,423 subscribers

111,859 görüntüleme • 1 ay önce •via X (Twitter)

Bilim & TeknolojiHaberler & Politika
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

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

16,637 görüntüleme • 2 ay önce

DeepSeek V4 is free on NVIDIA right now 😳 1M context. MoE architecture. Built for coding and agents. → → sign up → select DeepSeek V4 → start No card, no billing. Go grab it.
0:19

DeepSeek V4 is free on NVIDIA right now 😳 1M context. MoE architecture. Built for coding and agents. → → sign up → select DeepSeek V4 → start No card, no billing. Go grab it.

Punch AI

59,778 görüntüleme • 18 gün önce

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 🐸

52,775 görüntüleme • 2 yıl önce

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

14,435 görüntüleme • 4 ay önce

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

850,228 görüntüleme • 7 ay önce

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 görüntüleme • 3 ay önce

We share our early research on building Software World - a "GitHub" run by agents. We deploy agents for Python packages in a dependency chain, and each agent is tasked with collaborating with others and optimizing the package it owns.
0:13

We share our early research on building Software World - a "GitHub" run by agents. We deploy agents for Python packages in a dependency chain, and each agent is tasked with collaborating with others and optimizing the package it owns.

Shannon Shen

36,511 görüntüleme • 15 gün önce

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 görüntüleme • 7 ay önce

Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, delivering both higher throughput and lower latency in one architecture without sacrificing efficiency.
0:10

Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, delivering both higher throughput and lower latency in one architecture without sacrificing efficiency.

OpenAI

3,052,397 görüntüleme • 24 gün önce

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

32,141 görüntüleme • 5 ay önce

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

13,021 görüntüleme • 7 ay önce

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.
0:10

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.

Alvaro Cintas

15,555 görüntüleme • 4 gün önce

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

188,627 görüntüleme • 1 yıl önce

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.
0:15

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.

Stefan 3D AI

26,272 görüntüleme • 2 ay önce

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

171,158 görüntüleme • 3 ay önce

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)
0:18

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)

Avid

45,030 görüntüleme • 1 ay önce

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

47,432 görüntüleme • 2 ay önce

🎉 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

49,464 görüntüleme • 2 ay önce

Holy moly: GLM-5.3 got much better in cybersecurity since our pre-release evaluation with Z.ai. It now matches GPT-5.6-Sol on our cybersecurity benchmark at 0.4x the cost 🤯 - At pass@1: it went from 60.4% to 65.6% CVEs rediscovered, crushing every other open model on one-shot tasks - At pass@3: it did 75% -> 78.1%, matching GPT-5.6-Sol - Its precision remained stable, reporting fewer false positives than DeepSeek models The performance increase comes from a behavioral change: the new version is more persistent. It tends to run longer, and had a ~43% reasoning tokens increase. But the performance upgrade is worth that additional cost. 1/3 🧵
0:12

Holy moly: GLM-5.3 got much better in cybersecurity since our pre-release evaluation with Z.ai. It now matches GPT-5.6-Sol on our cybersecurity benchmark at 0.4x the cost 🤯 - At pass@1: it went from 60.4% to 65.6% CVEs rediscovered, crushing every other open model on one-shot tasks - At pass@3: it did 75% -> 78.1%, matching GPT-5.6-Sol - Its precision remained stable, reporting fewer false positives than DeepSeek models The performance increase comes from a behavioral change: the new version is more persistent. It tends to run longer, and had a ~43% reasoning tokens increase. But the performance upgrade is worth that additional cost. 1/3 🧵

pilvar (Philippe Dourassov)

34,484 görüntüleme • 28 gün önce