DigitalOcean - Videos

The Inference Economy: How Venture Is Betting on the Agentic Era

Leading investors break down the economics of scaling AI in production, from infrastructure bottlenecks to open vs. closed ecosystems, and share their predictions for what the AI industry will look...

Your Model Doesn't Matter. Your Infrastructure Does.

Everyone has access to the same models. So what actually matters? It's everything around them – routing requests to the right model, connecting to live data, scaling from prototype to production wi...

Open by Design: How NVIDIA and DigitalOcean Are Building the Stack for the Always-On Agentic Era

Kari Briski, VP Gen AI, NVIDIA, and Salman Paracha, SVP AI, DigitalOcean discuss why AI-native teams are demanding openness, model flexibility, and infrastructure built for agents that never sleep ...

Hard-Won Lessons from Teams Running High Volume Inference Workloads in Production

Scaling inference isn't a model problem. It's a decisions problem. Industry leaders from Workato Research Lab, ISMG, and Hippocratic AI share the decisions, tradeoffs, and investments that got them...

The Cost Cliff: Improve Your Tokenomics as you Grow, ft. Character.AI & Inferact.

70% of AI spend is now inference. See how Character.AI partnered with Inferact and DigitalOcean to cut inference costs by 50%, while improving throughput, on AMD GPUs. Speakers: Archana Kamath, VP...

Your Model Is Only as Good as Its Memory, with Weaviate

Your model isn't failing because it can't reason. It's failing because it doesn't have the right information at the right time. In this session, we'll dig into the data layer: the part of your AI s...

AI Disruptors: How the Next Generation of Business is Being Built

Early-stage founders building real AI companies today—what they’re solving, what’s getting in the way, and how they’re pushing through it. Moderator: Dinesh Murthy, Director of Product Management,...

DigitalOcean - Deploy Keynote - 2026

🚀 Join the Developer Cloud: https://cloud.digitalocean.com/registrations/new?utm_source=youtube&utm_medium=organic_video&utm_campaign=digitalocean&utm_content= // STAY CONNECTED 🌏 Follow our blog...

Don't use speculative decoding until you watch this

In this video, I benchmark speculative decoding with Llama-3-70B on an H100 GPU pairing it with 8B and 1B draft models, testing GPTQ and bitsandbytes quantization, and even trying ngram speculation...

What happens to AI reasoning quality when you compress a model? We tested it!

In this video, I benchmark Mistral-7B-Instruct-v0.2 on an NVIDIA H200 DigitalOcean GPU in three formats: FP16, INT8, and 4-bit AWQ — and test how precision impacts reasoning quality, speed, VRAM us...

KV-Aware Routing: How Workato AI Lab Slashed GPU Costs by 40%

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

NVIDIA B300 Blackwell Ultra: A Technical Deep Dive

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

How to Evaluate Agents in Production

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

GPU Programming for Beginners | ROCm + AMD Setup to Edge Detection

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

Deploy OpenClaw on WhatsApp in under 4 Minutes!

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

Is AI Killing Open Source? (I Was Wrong)

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

I built a CLI that forces me to think before coding

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

Pay less for LLM inference (Tip #2: Quantization)

Double your GPU capacity instantly with 8-bit Quantization You can serve twice as many users on the same GPU by switching from 16-bit to 8-bit precision. This reduces VRAM usage without degrading ...

Antigravity Skills Give You an Unfair Advantage

Stop starting from scratch every time you open a new project! In this tutorial, we show you how to use Agent Skills in Antigravity to create reusable, intelligent instructions that automatically ap...

Why LLMs are expensive to run (and how to fix)

Stop overpaying for GPUs: The AMD vs. CUDA breakdown GPU scarcity is driving prices 2-3x above MSRP, but vendor lock-in is finally breaking. See how open-source alternatives like ROCm let you use ...

LlamaIndex Integration for DigitalOcean Gradient™ AI Platform

DigitalOcean Gradient AI Platform now speaks LlamaIndex natively! Two new open-source packages let you connect your Gradient Knowledge Base and LLMs directly into your LlamaIndex pipelines: 📦 lla...

Claude Skills clearly explained in under 10 minutes

Have you noticed that AI often gets worse as you add more context? Longer chats, messier answers. In this video, I explain Claude Skills, Anthropic’s approach to fixing context overload. You’ll l...

3 tips for managing AI costs (50% cost reduction)

Stop overpaying for AI inference! In this video, we reveal 3 battle-tested strategies for slashing your LLM costs - proven techniques we used to cut Character AI's production inference costs by 50%...

Deploy Moltbot on DigitalOcean in Minutes | Secure Cloud Setup Tutorial

The last chapter was built for training. DigitalOcean is for what comes next! 🚀 Join us at Deploy San Francisco 2026 to learn about the modern Inference Cloud. ⭐ Save your spot: https://www.digita...

Add Cron to DigitalOcean Droplets

Most software doesn’t do its work when someone clicks a button. It runs in the background. In this video, I build a tiny system from scratch: - a DigitalOcean droplet (a Linux machine in the cloud...

How AI models run on GPUs (CUDA vs. ROCm)

Ever wondered how your Python code actually runs on a GPU? In this video, we break down the AI compute stack—the layers of technology that transform your high-level PyTorch commands into calculatio...

NPM Supply Chain Attacks Explained (And How To Stop Them)

Supply Chain Attacks are now becoming common, and one of the great examples was the NPM Great Heist which impacted 18 NPM packages with more than 2.5+ Billion Downloads weekly. Such attacks affect ...

How to rebuild a $12M AI App in 12 Minutes with no code (n8n + lovable)

I rebuilt a $7M app in under 30 minutes, without writing a single line of code. In this video, I show you how to clone a real, revenue-generating app like Yuka using Lovable and n8n and how you ca...

How to SSH into a GPU Droplet in VSCode | DigitalOcean Basics

In this video, you’ll learn how to SSH into a DigitalOcean GPU Droplet using VS Code step by step. Instead of using the terminal, we’ll use Visual Studio Code’s Remote Development extension to get ...

I Built My Own 2025 Wrapped — Books, Sports and More (Tutorial)

Here's how I learned how much money💵 I saved this year by going to the library: I scraped that data with Playwright and combined it with my Goodreads and Strava data (which I exported as 2 separate...

How to Create a GPU Droplet on DigitalOcean

Unlock the full power of DigitalOcean GPU Droplets with this step-by-step guide! In this video, you’ll learn exactly how to create a GPU Droplet from scratch, connect to it, install essential tools...

Which is your favorite git command? #coding #ai #programming

Build a Full Stack AI SaaS for $0 (Antigravity + DigitalOcean)

🚀 I Took the Ultimate Free Stack Challenge — and Built a Full-Stack AI App with ONE Prompt! In today’s video, I’m pushing the limits of what’s possible with free developer tools. We’re building an...

Cursor tips in 10 minutes

Using Cursor for coding? You're probably missing out on features that could save you a ton of time. In this video, I'll show you the Cursor tips and tricks I use every day to code faster and get be...

Why this AI plays video games like a human (SIMA-2 Breakdown)

🎮 SIMA 2 is HERE! (5 Things You Need to Know) Google recently dropped SIMA 2, and it’s a massive upgrade to their generalist AI agent. By using Gemini as its base model, SIMA has evolved from a si...

prompt ➜ check ➜ improve ➜ repeat: Until the research is spot-on!

How to Build an Auto-Updating Knowledge Base for AI Agents Using Real Data

I built a real-time NBA🏀 stats agent using DigitalOcean’s Gradient AI. Watch it answer “Who’s leading the league right now in {insert stat}?” by pulling fresh data daily straight from nba.com/stats...

I accidentally built a full AI chat app… in my terminal 😅

Built a tiny TUI with Textual that somehow turned into a full AI chat app. Powered by DigitalOcean’s Inference API — model switching, a status widget, and even dad jokes… all inside the terminal. ...

Google’s new step towards AGI

🚀 SIMA 2 is INSANE! (Google's step towards AGI) Google's says SIMA 2 is a "a significant step in the direction of AGI". It can understand and reason in complex 3D environments, but the secret to i...

Learn Image Prompting by Playing a Game

GitHub Repo: https://github.com/digitalocean-labs/image-prompting-game 🚀 Join the Developer Cloud: https://cloud.digitalocean.com/registrations/new?utm_source=youtube&utm_medium=organic_video&utm_...

vLLM: Introduction and easy deploying

Running large language models locally sounds simple, until you realize your GPU is busy but barely efficient. Every request feels slow, and most of that GPU power just sits idle. In this video, yo...

n8n course in 1 minute

A complete n8n course recapped in 1 minute ⏰😄

Complete n8n course (in 2 minutes)

Here's a recap of our free n8n crash course, which takes you from the basics to building a full-fledged, AI-powered workflow from scratch. This series is a practical, project-based guide. We won'...

Stop Paying for Slack. Host Your Own Chat App (Campfire Setup Guide)

What if Slack or Discord didn’t cost you a dime — and you owned the chat app outright? That’s Campfire. Originally built by the team behind Basecamp, HEY, and Ruby on Rails, Campfire is back — now...

How to Build a Simple AI Agent Using LangGraph in 5 minutes

AI Agents are becoming the go‑to solution for handling complex workflows—and LangGraph’s ReAct agent pattern makes it feel effortless. In this video, I will walk through a practical demo of analy...

Hacktoberfest wrap-up

As Hacktoberfest comes to a close, it's time to celebrate the incredible open-source contributions made around the world! Join us for the wrap-up event featuring inspiring stories from contributor...

How to Run Fal.ai models on DigitalOcean | 2 Minute Tutorial

Fal AI models are on DigitalOcean's Gradient AI platform! Learn how to run fal image generation and audio generation models in Python from a Streamlit application. Why use DigitalOcean for serverl...

How to Deploy Streamlit Apps to DigitalOcean App Platform

For developers working with Python, particularly those creating applications that leverage Gradient AI's serverless inference capabilities, the Streamlit web framework offers an exceptionally strai...

How to Migrate Droplets to DigitalOcean Managed Databases

Migrating your Droplets doesn't have to be complicated! We're here to make it easy. Join our webinar on 10/29 at 8AM PST/11AM EST to learn just how easy it is to migrate your Droplets to DigitalO...

Build a secure n8n authentication workflow 🔒 | COMPLETE n8n crash course [Part 9]

PROMO CODE 🚀 The first 50 people to redeem the promo code DOCODEYT will get $20 in free credits! https://cloud.digitalocean.com/registrations/new?utm_source=youtube&utm_medium=organic_video&utm_cam...