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.

Inference providers hate this man... Your LLM deployment can deliver 30 to 50% better performance after initial deployment. If your current inference provider isn't learning your workload and tuning the stack continuously after deployment, you need another provider. Wafer's continual inference agents do that work. Wafer's continual inference agents... profile your production workload to identify where scheduling, decoding, or GPU memory pressure limits performance. The agents benchmark changes to batching, serving engines, and GPU kernels against your workload. Each candidate must preserve correctness and meet your reliability targets before it ships. The agents keep profiling as traffic changes, identifying new bottlenecks and further opportunities to improve performance per dollar. Watch emilio andere explain how that work continues after deployment in his conversation with theCUBE.show more

wafer

14,421 subscribers

42,840 views • 25 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

15 Comments

wafer25 days ago

yes exactly

steve25 days ago

they HATE this guy

wafer25 days ago

lollll

wafer25 days ago

thank you to @bjbaumann2014, @Furrier, @theCUBE, @GemmaAllenSays, @DVellante for featuring us!

John Hahn25 days ago

nah no hate on MY ceo

wafer25 days ago

facts!

emilio andere25 days ago

loll do they?

wafer25 days ago

idk man

brian !25 days ago

@gpuemi this is dope

JV25 days ago

bro gets ALL the hate

wafer25 days ago

undeserved btw

Mira Takes25 days ago

Post-deployment tuning is where inference economics become an engineering feedback loop. The strongest providers will expose enough observability to show which workload signals drive optimization without turning customer data into a black box.

Mira Takes25 days ago

That 30–50% improvement highlights why deployment feedback loops matter. Models should be evaluated on the workload they actually serve, with observability and rollback paths making optimization safer than a one-time benchmark race.

Deep25 days ago

the tuning after launch is the part most teams skip. picking a provider is not a one time thing.

Stephen Fernandes24 days ago

The Best Inference Company !!! 🔥🔥🔥

Related Videos

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.

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

16,103 views • 2 months ago

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Fraction AI

67,922 views • 1 year ago

Debugging agents shouldn’t feel like detective work. Today, we’re excited to release two new AI agent interfaces that make agent observability & evaluations even more effective. 🔎 Timeline View – See execution flow and bottlenecks at a glance. No more guessing where your agent gets stuck. 💬 Conversation View – Experience exactly what your users see. Debug from the user's perspective, not just the system's. Combined with last week's Graph View, you now have three complementary ways to debug your agents: → Graph: Visualize decision paths and tool usage → Timeline: Spot performance bottlenecks instantly → Conversation: See the user experience end-to-end AI evaluations + observability are crucial to building reliable AI. These interfaces make it simpler to identify blockers and improve your agents faster. See all three views in action, and try it free with the link below 👇

Debugging agents shouldn’t feel like detective work. Today, we’re excited to release two new AI agent interfaces that make agent observability & evaluations even more effective. 🔎 Timeline View – See execution flow and bottlenecks at a glance. No more guessing where your agent gets stuck. 💬 Conversation View – Experience exactly what your users see. Debug from the user's perspective, not just the system's. Combined with last week's Graph View, you now have three complementary ways to debug your agents: → Graph: Visualize decision paths and tool usage → Timeline: Spot performance bottlenecks instantly → Conversation: See the user experience end-to-end AI evaluations + observability are crucial to building reliable AI. These interfaces make it simpler to identify blockers and improve your agents faster. See all three views in action, and try it free with the link below 👇

Galileo, now part of Cisco

499,481 views • 1 year ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

162,339 views • 6 months ago

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Zeb Evans

320,989 views • 9 months ago

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

LangChain

26,513 views • 8 months ago

New course: Add voice to your AI agents and applications, built with Vocal Bridge (disclosure: an AI Fund portfolio company) and taught by its CEO Ashwyn Sharma. Voice applications historically required making a hard tradeoff: using fast voice-to-voice models that sacrifice reliability, or accurate speech-to-text pipelines that add latency. This course teaches you how to build voice agents that are both reliable and fast. You'll build three types of voice-enabled applications: a voice-interactive game where voice commands and mouse clicks work together over a single channel, an agent that gains a voice in about 10 lines of code without touching its prompts or tools, and an agent that places outbound phone calls using a make_phone_call function. Skills you'll gain: - Add a voice layer to an existing agent without rewriting your prompts, RAG pipeline, or tools - Give an agent the ability to place outbound calls and stream transcripts back live - Set up voice evaluation to score calls, catch regressions, and improve quality before deployment Join and add voice to your agents without overhauling your architecture:

New course: Add voice to your AI agents and applications, built with Vocal Bridge (disclosure: an AI Fund portfolio company) and taught by its CEO Ashwyn Sharma. Voice applications historically required making a hard tradeoff: using fast voice-to-voice models that sacrifice reliability, or accurate speech-to-text pipelines that add latency. This course teaches you how to build voice agents that are both reliable and fast. You'll build three types of voice-enabled applications: a voice-interactive game where voice commands and mouse clicks work together over a single channel, an agent that gains a voice in about 10 lines of code without touching its prompts or tools, and an agent that places outbound phone calls using a make_phone_call function. Skills you'll gain: - Add a voice layer to an existing agent without rewriting your prompts, RAG pipeline, or tools - Give an agent the ability to place outbound calls and stream transcripts back live - Set up voice evaluation to score calls, catch regressions, and improve quality before deployment Join and add voice to your agents without overhauling your architecture:

Andrew Ng

97,401 views • 3 months ago

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.

elvis

249,243 views • 5 months ago

We just open-sourced Simulang, a JavaScript library that gives you and your coding agents the ability to fully control computers. Simulang is our scripting framework for desktop automation. It allows you to write deterministic computer use code that can be replayed dozens if not hundreds of times. Much faster and cheaper, compared to LLM agents. It ships with a skill out of the box. That means you can turn natural language prompts into Simulang code directly, and your agent can now see the screen, click, type, and navigate. It gives your AI agents eyes and hands to control the computer like humans do. Try these things with Simulang: - upload your pile of invoices to the expense platform - find 50 people with specific criteria on LinkedIn - open your calculator app and do some math - find all buttons on your favorite app using accessibility tree - or draw a bunny with MS paint 🐰 In this demo, we show how Simulang took over when the coding agent couldn’t open and click on the target LinkedIn profile page. Give it a try:

Simular

14,515 views • 5 months ago

New course announcement: Semantic Caching for AI Agents, taught by Tyler Hutcherson and Iliya Zhechev from Redis. Semantic caching can significantly reduce your AI application's inference costs and latency. If someone asks "How do I get a refund?" and another later asks "I want my money back," semantic caching recognizes these mean the same thing so it can use a cached response instead of making another model call. This short course takes you from building your first semantic cache from scratch to implementing production-ready systems using Redis' open-source tools. Skills you'll gain: - Build semantic caches from scratch, then implement them using Redis' SDK with production features - Measure cache performance using hit rate, precision, recall, and latency - Enhance accuracy with threshold tuning, cross-encoders, LLM validation, and fuzzy matching Join and learn to reduce your agentic AI's costs and improve speed!

New course announcement: Semantic Caching for AI Agents, taught by Tyler Hutcherson and Iliya Zhechev from Redis. Semantic caching can significantly reduce your AI application's inference costs and latency. If someone asks "How do I get a refund?" and another later asks "I want my money back," semantic caching recognizes these mean the same thing so it can use a cached response instead of making another model call. This short course takes you from building your first semantic cache from scratch to implementing production-ready systems using Redis' open-source tools. Skills you'll gain: - Build semantic caches from scratch, then implement them using Redis' SDK with production features - Measure cache performance using hit rate, precision, recall, and latency - Enhance accuracy with threshold tuning, cross-encoders, LLM validation, and fuzzy matching Join and learn to reduce your agentic AI's costs and improve speed!

Andrew Ng

62,497 views • 10 months ago

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

LeRobot

23,339 views • 3 months ago

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

Alex Cheema

30,854 views • 3 months ago

Dylan Patel of SemiAnalysis says a worse GPU with better storage and memory now beats the best chip without them, so buying the newest GPU alone no longer wins inference. So, an AMD GPU with more memory can outperform Nvidia in some cases. "So what we have is we have over $80 million of compute, GPUs from Nvidia, AMD, TPUs from Google, Trainium from Amazon, and we run this benchmark constantly on the newest inference engine, newest drivers, newest PyTorch version, whatever it is." "Every day it runs on an automated CI, and we run it on all the latest Chinese models, from GLM, Zhipu, Moonshot, Kimi, Alibaba, all these models we run." "Initially, when we were benchmarking the difference between these chips and different engines, different schemes for parallelism, we were just running it fixed context length." "But now with Agent X, we've analyzed over $5 million worth of Claude Code traces. This is real production traffic that people have donated to us as well as internally generated. Now we know what the actual agent workload looks like." "And then as we implement that and run those benchmarks, it turns out yes, the chip you're using is very important, but now even more important is how are you handling this memory offload?" "And so while an Nvidia GPU is faster than an AMD GPU in most cases, because AMD GPUs have more memory, they actually end up outperforming in some cases." "Or you can have a worse GPU, but a much better storage solution, and now you can outperform what the best GPU can do without those solutions. So just buying the newest and latest GPU alone doesn't get you the best inference economics." "Actually, you need to layer in all these other innovations including storage and memory." [ Who's the top player on your chart? ] "That really is a difficult multivariable problem. And generally that means you need to have, yes, you need to have the best GPU, a GB300, but you also need to have the best storage solutions. And so I won't spoil who's the best right here, but I will say that storage solutions matter a lot and memory solutions matter a lot, as does your front-end networking. That matters a lot."

Dylan Patel of SemiAnalysis says a worse GPU with better storage and memory now beats the best chip without them, so buying the newest GPU alone no longer wins inference. So, an AMD GPU with more memory can outperform Nvidia in some cases. "So what we have is we have over $80 million of compute, GPUs from Nvidia, AMD, TPUs from Google, Trainium from Amazon, and we run this benchmark constantly on the newest inference engine, newest drivers, newest PyTorch version, whatever it is." "Every day it runs on an automated CI, and we run it on all the latest Chinese models, from GLM, Zhipu, Moonshot, Kimi, Alibaba, all these models we run." "Initially, when we were benchmarking the difference between these chips and different engines, different schemes for parallelism, we were just running it fixed context length." "But now with Agent X, we've analyzed over $5 million worth of Claude Code traces. This is real production traffic that people have donated to us as well as internally generated. Now we know what the actual agent workload looks like." "And then as we implement that and run those benchmarks, it turns out yes, the chip you're using is very important, but now even more important is how are you handling this memory offload?" "And so while an Nvidia GPU is faster than an AMD GPU in most cases, because AMD GPUs have more memory, they actually end up outperforming in some cases." "Or you can have a worse GPU, but a much better storage solution, and now you can outperform what the best GPU can do without those solutions. So just buying the newest and latest GPU alone doesn't get you the best inference economics." "Actually, you need to layer in all these other innovations including storage and memory." [ Who's the top player on your chart? ] "That really is a difficult multivariable problem. And generally that means you need to have, yes, you need to have the best GPU, a GB300, but you also need to have the best storage solutions. And so I won't spoil who's the best right here, but I will say that storage solutions matter a lot and memory solutions matter a lot, as does your front-end networking. That matters a lot."

Fireside Alpha

185,279 views • 2 months ago

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,738 views • 1 year ago

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with AMD and taught by Sharon Zhou. You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks. Skills you'll gain: - Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate - Look inside the model to see how attention and layers combine to predict the next token - Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs Join and understand what's really happening inside your LLMs:

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with AMD and taught by Sharon Zhou. You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks. Skills you'll gain: - Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate - Look inside the model to see how attention and layers combine to predict the next token - Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs Join and understand what's really happening inside your LLMs:

Andrew Ng

126,461 views • 5 months ago

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @pauleveritt@fosstodon.org. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @[email protected]. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!

Andrew Ng

466,554 views • 6 months ago

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

132,058 views • 1 year ago

New short course: Practical Multi AI Agents and Advanced Use Cases with crewAI. Learn to build and deploy advanced agent-based systems in real applications in this course, created with CrewAI and taught by its founder, João Moura! (Disclosure: I've made a small seed investment in CrewAI.) In this course, you’ll learn how to create advanced agent-based apps that use external tools, do performance testing, can be trained with human feedback, and perform multiple tasks with different large language models. You will build several practical agentic apps that provide real business value, such as an automated project planning system, lead scoring and engagement pipeline, customer support data analysis, and a robust content creation system. In detail, you will learn how to: - Create these multi-agent systems with the building blocks of tasks, agents, and crews, along with the different things that make them work, such as caching, memory, and guardrails. - Integrate your multi-agent application with internal and external systems. - Connect multiple agents in complex setups, including parallel, sequential, and hybrid configurations, and create flows involving multiple agentic applications working together. - Test your agentic workflow and train it using human feedback to optimize its performance for better and more consistent results. - Work with multiple LLMs in your multi-agent system, using the appropriate model sizes and providers to fit each agent’s specific task. - Start a project from scratch in your environment and prepare it for deployment. You’ll also learn from an interview between João and Jacob Wilson, the Commercial GenAI Principal at PwC , in which they discuss deploying agentic workflows in real industry use cases. By the end of this course, you will be equipped to start building custom multi-agentic systems for your work. Please sign up here!

New short course: Practical Multi AI Agents and Advanced Use Cases with crewAI. Learn to build and deploy advanced agent-based systems in real applications in this course, created with CrewAI and taught by its founder, João Moura! (Disclosure: I've made a small seed investment in CrewAI.) In this course, you’ll learn how to create advanced agent-based apps that use external tools, do performance testing, can be trained with human feedback, and perform multiple tasks with different large language models. You will build several practical agentic apps that provide real business value, such as an automated project planning system, lead scoring and engagement pipeline, customer support data analysis, and a robust content creation system. In detail, you will learn how to: - Create these multi-agent systems with the building blocks of tasks, agents, and crews, along with the different things that make them work, such as caching, memory, and guardrails. - Integrate your multi-agent application with internal and external systems. - Connect multiple agents in complex setups, including parallel, sequential, and hybrid configurations, and create flows involving multiple agentic applications working together. - Test your agentic workflow and train it using human feedback to optimize its performance for better and more consistent results. - Work with multiple LLMs in your multi-agent system, using the appropriate model sizes and providers to fit each agent’s specific task. - Start a project from scratch in your environment and prepare it for deployment. You’ll also learn from an interview between João and Jacob Wilson, the Commercial GenAI Principal at PwC , in which they discuss deploying agentic workflows in real industry use cases. By the end of this course, you will be equipped to start building custom multi-agentic systems for your work. Please sign up here!

Andrew Ng

341,528 views • 2 years ago

Most AI coding setups right now look something like this: one agent in a terminal, another in a browser tab, a chat window somewhere else, and you in the middle copy-pasting diffs like a very tired air traffic controller. JetBrains just launched something aimed right at that mess. It's called JetBrains Air, and it lives inside their IDEs. The short version: Air lets you direct multiple coding agents, run their tasks in parallel, and review their work without ever leaving your IDE. Here's what stood out to me: 👇 1. You pick the agents. Air isn't tied to a single agent or provider. You can use the ones you already like. That matters more than it sounds, because the "best" coding agent changes every few months, and nobody wants to rebuild their whole workflow each time. 2. Parallel work without losing track. You can run several agent sessions at once, even across different projects. Air shows you where your attention is needed, so you're not hopping between tabs to find out which agent is stuck. 3. You stay in control. You can follow what each agent is doing, give it input, inspect the changes, and review the output before accepting anything. Nothing lands in your codebase just because an agent felt confident. 4. The agents get IDE smarts too. This is the part I find most interesting. JetBrains IDEs already have great code navigation, refactoring, testing, and debugging. With Air, both you and your agents work with that context. So the agents aren't guessing blind inside a chat box, and when something needs a human, the real tools are right there. The bigger idea here is that agents become part of your development workflow instead of a separate chat you keep switching to. There's also a nice bonus. For a limited time, JetBrains is offering Junie Lite for free (fair use applies). It's their own coding agent paired with a highly efficient model. It isn't pitched as a frontier-level agent. Think of it as a solid, free baseline for trying out Air and running everyday tasks. Air works in any JetBrains IDE and is in early access right now. If you write code with agents, give it a try: #ad

Most AI coding setups right now look something like this: one agent in a terminal, another in a browser tab, a chat window somewhere else, and you in the middle copy-pasting diffs like a very tired air traffic controller. JetBrains just launched something aimed right at that mess. It's called JetBrains Air, and it lives inside their IDEs. The short version: Air lets you direct multiple coding agents, run their tasks in parallel, and review their work without ever leaving your IDE. Here's what stood out to me: 👇 1. You pick the agents. Air isn't tied to a single agent or provider. You can use the ones you already like. That matters more than it sounds, because the "best" coding agent changes every few months, and nobody wants to rebuild their whole workflow each time. 2. Parallel work without losing track. You can run several agent sessions at once, even across different projects. Air shows you where your attention is needed, so you're not hopping between tabs to find out which agent is stuck. 3. You stay in control. You can follow what each agent is doing, give it input, inspect the changes, and review the output before accepting anything. Nothing lands in your codebase just because an agent felt confident. 4. The agents get IDE smarts too. This is the part I find most interesting. JetBrains IDEs already have great code navigation, refactoring, testing, and debugging. With Air, both you and your agents work with that context. So the agents aren't guessing blind inside a chat box, and when something needs a human, the real tools are right there. The bigger idea here is that agents become part of your development workflow instead of a separate chat you keep switching to. There's also a nice bonus. For a limited time, JetBrains is offering Junie Lite for free (fair use applies). It's their own coding agent paired with a highly efficient model. It isn't pitched as a frontier-level agent. Think of it as a solid, free baseline for trying out Air and running everyday tasks. Air works in any JetBrains IDE and is in early access right now. If you write code with agents, give it a try: #ad

Mushfiq Sajib

40,469 views • 7 days ago