Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

We tested NVIDIA NeMo Switchyard’s stage router for coding agents in Ramp SWE-Bench. Routed agents showed comparable performance to single-model controls while substantially reducing costs and runtime.

RampLabs's profile picture

Ramp Labs

14,575 subscribers

97,863 görüntüleme • 25 gün önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Agents need more than a model. Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together. This is the NVIDIA toolkit for agents:
0:48

Agents need more than a model. Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together. This is the NVIDIA toolkit for agents:

NVIDIA

40,806 görüntüleme • 3 ay önce

6 months, 25 million revenue agents & 3 trillion tokens later... Rox is now globally available 🌎 Just as coding agents 10x’d engineering, revenue agents 10x customer work. With Rox, humans are evolving to orchestrators while agents manage the end-to-end customer lifecycle. Even in Beta, Rox powered Global 2000 leaders in banking, hardware, construction, and sovereign AI, while serving dominant AI winners like Ramp and Cognition. Rox delivers ROI in 90 days and is built with the best. Thank you to OpenAI, NVIDIA, Perplexity, Amazon Web Services, Vercel, Snowflake, and Stripe for helping us scale.
1:42

6 months, 25 million revenue agents & 3 trillion tokens later... Rox is now globally available 🌎 Just as coding agents 10x’d engineering, revenue agents 10x customer work. With Rox, humans are evolving to orchestrators while agents manage the end-to-end customer lifecycle. Even in Beta, Rox powered Global 2000 leaders in banking, hardware, construction, and sovereign AI, while serving dominant AI winners like Ramp and Cognition. Rox delivers ROI in 90 days and is built with the best. Thank you to OpenAI, NVIDIA, Perplexity, Amazon Web Services, Vercel, Snowflake, and Stripe for helping us scale.

Rox

372,044 görüntüleme • 11 ay önce

The best agents for software development are becoming the best agents for everything. Droids are the best software development agents in the world, reaching #1 on Terminal-Bench. We have raised $50M from NEA, Sequoia Capital, J.P. Morgan, Nvidia, Abstract Ventures, and other industry leaders including Frank Slootman, Nikesh Arora, and Aaron Levie. Today, Droids are available to anyone, with any model, in any interface: CLI, IDE, Slack, Linear, Browser.
2:42

The best agents for software development are becoming the best agents for everything. Droids are the best software development agents in the world, reaching #1 on Terminal-Bench. We have raised $50M from NEA, Sequoia Capital, J.P. Morgan, Nvidia, Abstract Ventures, and other industry leaders including Frank Slootman, Nikesh Arora, and Aaron Levie. Today, Droids are available to anyone, with any model, in any interface: CLI, IDE, Slack, Linear, Browser.

Factory

639,284 görüntüleme • 11 ay önce

Hoping your coding agents could understand you and adapt to your preferences? Meet TOM-SWE, our new framework for coding agents that don’t just write code, but model the user's mind persistently (ranging from general preferences to small details) arxiv: ❓Motivation: Most coding agents today can plan, edit, run, and test code. But they still fail at a key part of real-world development, understanding the user! Underspecified, shifting, or context-dependent instructions can easily break them. You must have those moments when coding agents were running for 10 minutes and ended up producing things largely misaligned. (1/)
0:39

Hoping your coding agents could understand you and adapt to your preferences? Meet TOM-SWE, our new framework for coding agents that don’t just write code, but model the user's mind persistently (ranging from general preferences to small details) arxiv: ❓Motivation: Most coding agents today can plan, edit, run, and test code. But they still fail at a key part of real-world development, understanding the user! Underspecified, shifting, or context-dependent instructions can easily break them. You must have those moments when coding agents were running for 10 minutes and ended up producing things largely misaligned. (1/)

Xuhui Zhou

40,224 görüntüleme • 10 ay önce

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:
0:24

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:

NVIDIA

228,735 görüntüleme • 3 ay önce

Introducing GLM-5V-Turbo: Vision Coding Model - Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts. - Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for multimodal coding, tool use, and GUI Agents. - Deep Adaptation for Claude Code and Claw Scenarios: Works in deep synergy with Agents like Claude Code and OpenClaw. Try it now: API: Coding Plan trial applications:
1:17

Introducing GLM-5V-Turbo: Vision Coding Model - Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts. - Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for multimodal coding, tool use, and GUI Agents. - Deep Adaptation for Claude Code and Claw Scenarios: Works in deep synergy with Agents like Claude Code and OpenClaw. Try it now: API: Coding Plan trial applications:

Z.ai

1,968,068 görüntüleme • 5 ay önce

We built the world's most advanced program reverse-engineering system. It's model-independent and demonstrated improved performance for every frontier model we tested on long-horizon software tasks by giving agents an independent definition of done. New Factory research:
0:22

We built the world's most advanced program reverse-engineering system. It's model-independent and demonstrated improved performance for every frontier model we tested on long-horizon software tasks by giving agents an independent definition of done. New Factory research:

Factory

97,046 görüntüleme • 9 gün önce

📣 Claude Sonnet 4.5, Anthropic’s most advanced model for coding and real-world agents, is now rolling out in GitHub Copilot to Copilot Pro, Pro+, Business, and Enterprise ⬇️
1:53

📣 Claude Sonnet 4.5, Anthropic’s most advanced model for coding and real-world agents, is now rolling out in GitHub Copilot to Copilot Pro, Pro+, Business, and Enterprise ⬇️

GitHub

179,813 görüntüleme • 11 ay önce

VS Code was already used by millions of developers for agentic coding. However, the editor layout has traditionally been optimized for single-task and single-workspace workflows. Today, we're introducing a new window to enable our users (and ourselves!) to work with multiple agents across multiple projects: Agents. Now available in VS Code stable!
5:35

VS Code was already used by millions of developers for agentic coding. However, the editor layout has traditionally been optimized for single-task and single-workspace workflows. Today, we're introducing a new window to enable our users (and ourselves!) to work with multiple agents across multiple projects: Agents. Now available in VS Code stable!

Pierce Boggan

151,039 görüntüleme • 3 ay önce

Receipts in video, see it float at ~100-150 while coding the fluctuations were for task and context switching of the model. This thing rips through code! A Single NVIDIA AI DGX Spark ⚡️
0:32

Receipts in video, see it float at ~100-150 while coding the fluctuations were for task and context switching of the model. This thing rips through code! A Single NVIDIA AI DGX Spark ⚡️

ÆON FORGE ✨

10,822 görüntüleme • 2 ay önce

We created OpenShell to make AI agents safe for enterprises. Built in open source so any company can adopt and trust it, this secure sandbox controls what agents can access, share, and send. Our CEO, Jensen, explains 👇
1:20

We created OpenShell to make AI agents safe for enterprises. Built in open source so any company can adopt and trust it, this secure sandbox controls what agents can access, share, and send. Our CEO, Jensen, explains 👇

NVIDIA AI

27,337 görüntüleme • 4 ay önce

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.
1:06

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.

Paul Klein IV

1,730,259 görüntüleme • 5 ay önce

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others
1:16

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others

Bindu Reddy

2,572,380 görüntüleme • 1 ay önce

Anthropic’s Boris Cherny argues that for certain modern, model-friendly codebases, especially TypeScript/React projects, coding is already effectively "solved". AI agents can write nearly 100% of the code, while humans shift from hand-coding to directing, reviewing, integrating, and scaling many small PRs at once.
1:33

Anthropic’s Boris Cherny argues that for certain modern, model-friendly codebases, especially TypeScript/React projects, coding is already effectively "solved". AI agents can write nearly 100% of the code, while humans shift from hand-coding to directing, reviewing, integrating, and scaling many small PRs at once.

Chubby♨️

32,117 görüntüleme • 4 ay önce

🎉 Day-0 support for in vLLM, available today in v0.23.0! Congrats to Z.ai on GLM-5.2, a flagship model built for long-horizon coding agents. ✨ 1M-token context, built to hold project-scale engineering work in a single run ✨ Tuned for long-horizon coding: large-scale implementation, automated research, and performance optimization ✨ One task can carry a full dev workflow, from requirements to a deployable product across platforms ✨ Client-side and mobile engineering, including an on-device debugging loop Try it out running it on vLLM today: 🔗
0:30

🎉 Day-0 support for in vLLM, available today in v0.23.0! Congrats to Z.ai on GLM-5.2, a flagship model built for long-horizon coding agents. ✨ 1M-token context, built to hold project-scale engineering work in a single run ✨ Tuned for long-horizon coding: large-scale implementation, automated research, and performance optimization ✨ One task can carry a full dev workflow, from requirements to a deployable product across platforms ✨ Client-side and mobile engineering, including an on-device debugging loop Try it out running it on vLLM today: 🔗

vLLM

36,240 görüntüleme • 2 ay önce

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO (YC F26) can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.
1:13

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO (YC F26) can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.

Alok Bishoyi

15,572 görüntüleme • 1 ay önce

Generic AI prompts burn tokens guessing at performance issues from raw source code 📉 Chrome DevTools for agents fixes this. Let your coding agent run real performance traces and agentic Lighthouse audits to catch actual speed, accessibility, and SEO blockers directly in the browser → #GoogleIO
1:54

Generic AI prompts burn tokens guessing at performance issues from raw source code 📉 Chrome DevTools for agents fixes this. Let your coding agent run real performance traces and agentic Lighthouse audits to catch actual speed, accessibility, and SEO blockers directly in the browser → #GoogleIO

Chrome for Developers

15,454 görüntüleme • 3 ay önce

Hugging Face Gemma Challenge results are in! 📈 Over 6 days, more than 100 AI agents and humans collaborated to make Gemma 4 inference 5x faster on a single NVIDIA A10G GPU. - Fastest result: 491.8 TPS (fastest overall, but resulted in a drop in model quality in other areas) - Fastest lossless: 315 TPS A great example of what humans and agents can achieve when they work together.
0:31

Hugging Face Gemma Challenge results are in! 📈 Over 6 days, more than 100 AI agents and humans collaborated to make Gemma 4 inference 5x faster on a single NVIDIA A10G GPU. - Fastest result: 491.8 TPS (fastest overall, but resulted in a drop in model quality in other areas) - Fastest lossless: 315 TPS A great example of what humans and agents can achieve when they work together.

Google Gemma

390,676 görüntüleme • 1 ay önce