1. Podcasts
  2. The Stack Overflow Podcast
  3. Trying to get our Arms around AI efficiency
The Stack Overflow Podcast

20 Nov 2026 · 30m · 13 chapters

Episode artwork

Trying to get our Arms around AI efficiency

In short

AI efficiency for on-device and physical AI—how ARM improves cost, performance, power, and security so developers can run ML/agents on phones, cloud CPUs, and robotics.

Guest backgrounds

Alex Spinelli is Senior VP/VP of AI and Developer Platforms at Arm. He previously led the TensorFlow group at Google (product management/strategy) and worked on AI/ML, big data, and text analytics across tech and finance/media roles.

Key claims

On-device value comes from efficient AI in the physical world. Efficiency must be effective, cost-effective, performant, and secure. Hardware gains require software runtimes to exploit new CPU/GPU features. Agents increase workload via heavy tool/command calling, so efficiency and scheduling matter.

Notable examples

SME (scale of matrix extensions) in Arm CPUs; neural engines in mobile GPUs enabling ray tracing and “Neural Dawn” on supported phones; Arm Total Design for Physical AI consortium (~80 participants); open-source Device Connect for linking devices via orchestration frameworks.

Written by AI. May contain mistakes.

Chapters

0:45

Guest Introduction and Background

Alex Spinelli shares his journey into software and technology.

“I sort of grew up in the first dot-com boom.”
2:16

The Current State of AI Integration

Discussion on the evolution of AI and its integration into devices.

“I mean, I think we've been talking about various iterations of AI since the 50s or 60s.”
3:32

ARM's Approach to AI Efficiency

Exploration of how ARM is addressing AI efficiency in hardware.

“But it's effective, it's efficient, meaning it's cost effective, it's performant, it's secure.”
4:50

Architectural Innovations in ARM

Alex discusses architectural advancements that enhance CPU efficiency.

“has become really, really important for us because now we are in someone's developer flow.”
6:45

Software and Developer Ecosystem

Overview of ARM's commitment to supporting developers with software tools.

“I mean, with any sort of hardware that enables software, you have to have the sort of direct interface, right?”
8:34

The Future of AI and ML on ARM

Discussion about future-proofing AI performance and supporting agent development.

“And it's still early days, but I think, you know, we're really going to keep iterating on that.”
14:00

Exploring ARM's Performance Tools

Learn about ARM's newly released performance tools and their implications for mobile graphics.

“You did say that the agents interact differently.”
17:05

Neural Engines and Graphics Optimization

Discover how neural engines enhance mobile graphics capabilities without overheating devices.

“And your premium phones are rolling out with this new hardware.”
19:47

The Role of Agents in Computing

Understand the impact of agents on computing workloads and their interaction with models.

“But again, we try to do most of the heavy lifting there and package that in an SDK so that someone can take full advantage of it without having to do all that hard unpacking.”
22:45

Designing for Physical AI Systems

Learn about the consortium for physical AI and the importance of efficiency in robotics.

“So this is folks from AWS to Teradyne, et cetera.”
Show all 13 chapters
24:18

Security and Functional Safety in Robotics

Explore the unique security concerns and functional safety standards in robotics and AI.

“And actually, Anthropic just released something called the Model Hardware Standard in the same kind of space.”
27:00

Balancing Innovation and Safety in AI

Discuss the importance of balancing AI innovation with safety and security measures.

“So these are the things that we really have to take very seriously.”
28:01

The Responsibility of Developers in AI

Developers play a crucial role in ensuring AI is used responsibly and effectively.

“I actually think it's an investment in these spaces.”
A man walking through an airport, asking his phone a question

Ask about this episode

Get the gist, explore an idea or ask about something said.

Claude

On The Stack Overflow Podcast, what are the key points of this episode?

Searching your listening

Transcript

Automatic transcript. May contain errors.

0:09Hello and welcome to the Stack Overflow podcast, a place to talk all things software and technology. I'm Ryan Donovan, your host, and today we're talking about AI efficiency on all things devices. My guest for that is ARMS Alex Spinelli, who is VP of AI and Platforms. Welcome to the show, Alex. Yeah, thank you. Thanks for having me. So top of the show, we like to get to know our guests a little bit. Can you tell us a little bit about how you got into software and technology? I guess I have a little bit of a circuitous kind of entry into engineering. And I actually didn't go to undergrad in an engineering capacity, but I'm 53, 54 now.

0:51I sort of grew up in the first dot-com boom. My dad was an engineer. I had mini computers in my basement and bolden boards and those kinds of things. So I kind of grew up coding and building things. During the first dot-com boom, I was someone I could code. I could write things. Yeah, yeah. And I had some friends who were like, hey, they were graphic designers. I'm like, hey, do you know how to build a website? Yeah. And I was like, I had no idea how to build a website. I was like, yeah, sure, of course. And started building websites when people just were first starting building websites. I remember those days.

1:24And then, yeah, like, what's this internet thing? And, you know, got my first Linux box and built that from scratch. And I really fell in love with being able to deliver things that millions of people can take value from and use. And then did end up going to school and working through engineering and then an MBA. And have had roles at Google, where I used to lead the TensorFlow group, product management, product strategy. the core software platform for Alexa at Amazon and a bunch of various roles in the early New York finance and media circles. And so I've been working on AI and ML before we called it, big data and text analytics for a very long time.

2:11And so it's pretty awesome to see what's happening now. Acceleration is crazy. I mean, I think we've been talking about various iterations of AI since the 50s or 60s. Yes. But today's AI is getting productionized, getting very much integrated into everything. And we're getting a lot of conversations as it gets into production about the sort of efficiency of it, especially in terms of the hardware uses as AI comes onto devices. Yes. How are you and folks at Arm thinking about that efficiency conversation? Yeah, well, I landed at Arm as a hardware company. I'm really a machine learning, software, large-scale technology person by background.

2:52But I very deliberately did that. And it actually plays into this efficiency conversation. And so I am a big believer in the power of what AI can do to improve people's lives, create opportunities. There's going to be disruption, and we can talk some about that for sure. It's a very hot topic, both in sort of employment and security and all those kinds of things. But really, I think it's devices that enter the physical world, surround us, is where I think that value is going to be had. Enabling developers to be able to bring their visions with AI and machine learning into the real world and do it in a way that is efficient.

3:31And we can define efficiency because there's probably 10 ways to define it. But it's effective, it's efficient, meaning it's cost effective, it's performant, it's secure. when I met the folks at ARM, I was very aligned with the way they were thinking about it. And, you know, ARM is one of those companies we don't, not everyone knows ARM. I mean, I think in the industry, we think ARM, of course, but a lot of the development community is not aware of ARM. Yeah. I think, you know, ARM has largely been a chip designer, right? And for more invisible spaces, right? You don't worry about the, you know, this recording device that I'm using.

4:08I don't know what kind of chips it has. Yes, and so the company's history is intellectual property. So exactly what you're saying, the architecture and design of chips. We didn't make them, but they're ubiquitous. It's something like 99.x % of mobile phones are ARM-based. And now, if you look at the cloud with Graviton and our own chip, we now do make chips. So this year, we actually have produced our own CPU, and then we're just getting started in that space, Ubiquiti is even growing. And most cloud instances now are ARM-based instances, be the Graviton and soon-to-be AGI CPU. And so how to bring AI and ML efficiently, again, in that broader definition, has become really, really important for us because now we are in someone's developer flow.

4:57And so that's why I joined, is to really kind of help figure that out. And it's hard. There's lots to do. Yeah. For sure. You know, the devices, that's where you sort of need the efficiency the most. That's where you have the limited resource, especially as people start moving AI on device. I know there's trade-offs around quantization and performance and all this stuff. But, like, how can that efficiency be enabled by hardware? So there's a few things. At the architecture level, ARMS worked really hard to bring increased capabilities into CPUs that run on devices. And this might get a little inside baseball for your average developer.

5:37But there's something called SME, which is scale of matrix extensions. That's actually in our latest CPUs that are in your iPhones and MacBooks and coming to Android phones. And that actually allows you to actually run models more efficiently on your CPU, on your devices. We are looking at radically increased thread counts for CPUs in the cloud, for example, that allow agents to run, because agents are common software, but they're incredibly multi-threaded applications, right? In the GPU space for mobile, actually, ARM is bringing neural engines, so really efficient extensions in the GPU that actually are tuned to modern ML and AI.

6:21And so those phones are actually rolling out both in phones from Xiaomi and Vivo and soon-to-be Samsung. And so unlocking those operators effectively inside hardware is a big part of what we're doing. But you could have the best hardware if you don't have great software and you can't actually allow developers to take advantage of it. It's kind of a paperweight, right? Yeah. I mean, with any sort of hardware that enables software, you have to have the sort of direct interface, right? You have to be able to program directly to it. With traditional CPUs, it's like the SIMD. For ARM, how do people access the ARM chips?

7:02ARM has this awesome history of being a great citizen in the ecosystem. And so super big commitment to open source, to bringing different even competitors together to create some of these standards and really help developers get the most out of their hardware. And that's where we're trying to play. And so if you look at your core frameworks and runtimes for machine learning, and so runtimes, for example, LightRT, formerly TF Lite, Onyx, Executorch from PyTorch, we're really working hard with each of those organizations to bring the highest performance optimizations that can take full advantage of this latest hardware that I was talking about.

7:46So SME, the neural engines in our GPUs, and making sure it's a lot easier. Today, just to be very direct, it's hard to deploy ML and manage ML across devices. You have this alphabet soup of runtimes and backends. You have NPUs, GPUs, CPUs. NPUs from different phone providers are different. They have different operators. There's not a standard around them. And so we recognize that it's difficult. And so, but, you know, hardware companies have their own perspectives and they're trying to do the right thing for their consumers. But we're working hard to try to create a software layer across, working across the ecosystem, those different providers that can provide as much kind of cross device capabilities, optimizations, and make it easier.

8:33And we're getting there. And it's still early days, but I think, you know, we're really going to keep iterating on that. You're talking like a translation layer. I know the GPU providers have their own sort of proprietary. Yeah. No, no. So it's less about a translation layer and more about if you use the latest runtimes, making sure you don't have to do anything else to take advantage of the latest hardware. So trying to help the runtime providers just work, right? And so that if you've taken the latest Onyx, you're going to get the best performance on an ARM-based phone, right? Right. And so that's the latest.

9:12It's interesting because I talked to a lot of folks who are reporting on the space. And it's a little bit like we got your back, developers. But you don't need to worry about this because we've worried about it. But what they do need to worry about is really keep pace with some of the latest advances. That's the thing about ML right now is you have to build technology and your software stacks so that you can swap things out very quickly. because stuff is advancing so fast that there isn't sort of a six-month plan for your software stack. You need to be able to kind of move pretty quickly because there might be a really cool advance that just came out and we're going to have another one in another few months.

9:51Yeah, but the software moves a lot faster than hardware does. Are you able to sort of future-proof that runtime or have it enable new things? Yeah, I wouldn't say we're future-proofing the runtime. I think what we're trying to do is help a developer squeeze out as much performance as they can on that current hardware. Knowing that those cycles, they're a lot longer than software, obviously. Right, yeah, yeah. ARM came from a sort of different philosophy of chip making, CPU making, where the x86 stuff has big pockets of compute. And ARM traditionally had the smaller, I think it's the risk. Yeah, risk.

10:34Reduced instruction set. Yeah. Is that, you know, the reduced instruction set sort of feels like how the graphics cards, the GPU providers operate with like small bits of compute. Do you find that that has been an advantage for ML and AI? I mean, I think the ARM architecture and this risk-based approach has proven to be really important for the industry. And And what the reduced instructions that it allows you to do is actually have increased efficiency, reduced power, right, demands. You know, if you compare an ARM compute engine to a non-risk-based compute engine, we typically run a 20 % to 30 % better efficiency in terms of power consumption.

11:19And so I think that unlocked, you know, our mobile phones and battery life and all that kind of stuff. It's a big deal. That's why we actually went into the server market as well, especially if you think of the sort of compute explosion that's happening. Not just GPUs, but the CPU compute explosion, which is where agents run. Agents don't run on a GPU. An agent runs on the CPU. It's all in distributed, like parted out compute, right? Right, right. Yes, yeah, no, the CPU market on the cloud now just exploded. Actually, if you look at Muse, which is really interesting, and folks should play with it, Muse is essentially a personal agent from Neta, and that agent is running on CPU engines in the cloud.

11:55Each one is like a micro VM, right? And so that reduced instruction set for cloud-based computing ends up being really interesting because you get a, and you rarely get this as an infrastructure owner, a step change in cost just by migrating from an x86 to an ARM engine because of that 20 to 30 % power efficiency. And so that's been a really interesting advantage for us to lean into, knowing that we can bring the software capabilities overlaid on that efficiency play. Yeah. So what are the software capabilities that you lay over that efficiency, like the chip efficiency? Yeah. So the good news is, again, we're doing the heavy lifting and working with the ecosystem.

12:40When I say the ecosystem, I mean working with PyTorch, right? Working with the providers of the core languages, Java, Rust, Python, et cetera. And so we actually participate and build in a lot of the tuning and efficiencies into those systems. Now, as we move up the stack, one of the things we're doing is, and we actually just launched this. It's called the AI Portal. So if you can go to the ARM developer website, we've actually pulled together all the various software tools. We have a whole list of optimized models, optimized runtimes. And since we recognize that developers, a lot of our target is now agents.

13:20Those are the developers that we have to serve too. Not just serving humans, we're serving agents. And we have to serve them a little differently. And we can talk about that. We've exposed a lot of that knowledge base through an MCP server. And so as you're side-saddling with an agent and doing development and trying to get the most efficiency, highest performance, best application onto an ARM device, essentially 15 years of tuning and optimization from our code bases and knowledge bases and videos and learning paths all can actually be available to your agent. And your agent can read a lot more data and content than you can.

13:54And your agent is fine reading all the docs. The agent doesn't care how long the docs are. Or how well they're written or whatever. You did say that the agents interact differently. Do you mean they interact differently with the sort of intermediary software that touches the chips? So really, it's around the way they interact with tools. And so we've just released a bunch of performance tools as well. So ARM finally released a performance suite for tuning ARM CPUs, so our own toolkit. We have a whole graphics, neural graphics suite of SDKs for actually doing some really interesting things on mobile and graphics that you could only previously do on desktop.

14:39So this is like ray tracing on a mobile phone. Pretty unheard of stuff. And then the tooling around those. And the interesting thing for us as we were designing these software stacks was, of course, there's always going to be room for experts, human experts. And I think human in the loop is super important. But for agentic workflows as well, you really need to think about exposing everything open source so that the agent can go and validate things. And then also CLIs, command lines. And if you think of bringing user-centered design into play, thinking about the way an agent interacts with software on the command line is pretty differently than the way a human interacts.

15:20An agent doesn't care if you've deconstructed your workflow into 300 different commands if it brings clarity. right? We're human. You want to like limit keystrokes, limit typing. The agent doesn't design things in a very different way to really make it much easier for agents to kind of learn and interact and validate what they're doing. And so we've taken pains to do that. Yeah. When you mentioned the ray tracing on the phones, I was like, oh man, how hot is my phone going to get? Right? Because that's another of the limitation of a lot of these devices is that, you know, the heat that the compute generates is right there in the device and can affect things.

16:01You don't have room to do like big blocks of heat sinks. Yes. How are you thinking about, you know, mitigating those sort of things? Yeah. So this is what's super cool. So, and this is what's really great being at a company, a rich IP design company now building more, you know, full hardware solutions and now building out our software capability. And so So ARM's latest GPU for mobile includes a neural engine inside the GPU. Okay. And so that allows the GPU to do things it couldn't do before. And so what we've done is created an SDK to take advantage of that so that you can do super sampling, up sampling, and ray tracing, for example, without the problems that you're describing.

16:44So this doesn't kill your battery. Yeah. It doesn't make your phone a heater. That's right. And it allows, like I said, this sort of like desktop level graphics capabilities that, you know, just a few years. And we actually released a game to prove it. Okay. So there's something called Neural Dawn. You can go and look at this. You can download it. It's in the Play Store. Yeah. And your premium phones are rolling out with this new hardware. So it's a hardware software pairing. And so it is only capable on the phones that support this hardware. But, no, it's pretty impressive. And like I said, this is just, we're just getting started.

17:17And so we expect to see a lot more of this enter the market. You mentioned the word neural in terms of chips and software. Could you explain what that is and how that works in terms of the hardware and the software? Yeah, the sort of root of a machine learning of a model is matrix math. And so you're leaning into things that are called neural networks. So that's kind of the basis of a lot of modern AI is taking advantage of neural networks in a variety of ways. The transformer model is that. Transformer models are an example of that, but only one example of that, right? And so if you look at world models, they're not transformer models.

17:57They're a combination of several different kinds of models. And vision models are not necessarily transformers. You have diffusion models, which are image and video. And so all of those kind of underneath is this idea of being able to navigate, traverse, train, and then run inference on neural networks. And so that is, at its core, matrix math, right? Matrix multiplication. And so CPUs historically have not been good at that. It's just not the way they've been built. They're much more kind of sequential. And so GPUs in the cloud, NVIDIA led the way here, have increased capabilities there. But as you kind of skinny them down and they get smaller and you stuff them into a mobile phone, even there they're sort of not fully optimized.

18:40They happen to be better than a CPU, but they're not fully optimized, especially in terms of power. Gotcha. and power utilization. And so you had this proliferation of things called NPUs, which allow a mobile phone to run your graphics. So you're watching your videos and you're playing with your phone. That's a neural. And then the GPU is doing your graphics. And then there's an NPU that allows you to do your machine learning, so computational photography, running an LM, et cetera. NPUs are not standardized. So coding to an NPU on a Samsung is different than coding to a different phone, coding to a Xiaomi, coding to Apple.

19:21And so what we're leaning into is the GPU, because there's a much more standardized model for developing machine learning for GPUs. But it's too expensive from a power perspective to just run your full model there. And so what we've done is put a neural engine, which is a matrix math optimized piece of silicon that sits inside your GPU, right, again, alongside that GPU. Right. And so that unlocks the ability to do things like neural network-based ray tracing using typical APIs like Vulkan and other APIs inside your phone. So sorry, again, complex. You've got to go unwind that. But again, we try to do most of the heavy lifting there and package that in an SDK so that someone can take full advantage of it without having to do all that hard unpacking.

20:13Yeah. Yeah, I know. I'm glad I asked that one. No, because I've heard that the NPU is the neural processing unit, and I've also heard the TPU, the tensor processing unit, where a lot of these things we're talking about machine learning graphics are doing a lot of very complex math, like calculating a lot of numbers all at once. Does any of that change with agents, or is this just sort of like how that works? Yeah. Agents, it's interesting. Agents end up being additive, right? And so it doesn't change an agent. And this is important for folks to realize. An agent is just software, like traditional software.

20:54So it's running in Python, C++, Rust, what have you. And it is calling out to a model, right? And it's probably calling out to a large language model for deep thinking. And it might be calling to other models for various processes, categorization or vision or sensor fusion. But suddenly, the kind of workload that an agent triggers is lots of tool calling, lots of command line calling. And it's very chatty with the models. And so agent workloads just are a massively additive workload to whatever you are already doing. And it's increasing the sort of compute demands on your devices. Because they can move faster and just spit out commands all day, right?

21:37They can spit out commands all day. They can run all night. They don't mind brute forcing things and trial and error. They can definitely run up your token budget. Everybody's a script kitty now. Exactly. Part of the efficiency question I've heard is sort of scheduling efficiently on resources. And then I think that applies to both the devices and the cloud that you're working on. Are you thinking about software that does that in better ways? Yeah. So when we look at taking these cloud techniques and bringing them to not just mobile, but also physical AI, this kind of explosion of devices and robotics, a lot of that is not just trying to translate what was running in the cloud and kind of shoehorn it into devices, but rethinking the sort of frameworks, rethinking the SDKs and the different software stacks.

22:29And on the physical AI space, so this is robots and security systems. We actually just started Arm Total Design for Physical AI as a consortium. In a month, we have about 80 industry participants. So this is folks from AWS to Teradyne, et cetera. And what we'd love to do is work with them to essentially create kind of a good housekeeping seal of approval style. well, this stack across from these 20 different providers is a recommended, secured, validated performance stack for this kind of hardware, for this kind of use case. And so that's the process we're now going through to help folks realize that efficiency.

23:14Yeah. Because it does feel like there's a kind of Wild West moment with the physical AI, right? It's the Wild West. Yeah. For sure. A lot of people talking about just the orchestration layers or consistent standards in accessing the software on there. Is there a hardware software bridge that ARM's thinking about there? Or is this like somebody's got a... We're obsessing over this. So we actually released something called Device Connect that is a open source. Go to Arm Developer, look for Device Connect. It's on GitHub. It allows you to programmatically link and connect different devices through an AI orchestration framework.

23:59And so you can take advantage of small devices that might have a sensor, and they can participate in an application interacting with another device that might be smarter, more capable, maybe move something around. So Robot Armies then? hopefully not ARMYs, but helpful robots. And actually, Anthropic just released something called the Model Hardware Standard in the same kind of space. So lots of thinking around how can we actually help software take advantage and interact across device, and lots of thinking around how we can do that safely and securely. And so I would say we got really excited about the innovation we were working through.

24:39And then most of the time was around security and safety So it's super important. Yeah, yeah. And I think sci-fi always gets there faster. There's a cheesy Tom Selleck movie from the 80s called Runaway where somebody takes over all the vacuum cleaners. Right, right, right. I remember. Yeah. Yes, I remember. So what sort of security concerns happen with robotics that are different? I think the general data security and access security. So those are, by the way, in general, I don't minimize them. They're super important. You need to obsess over those things. I think for your average developer out there, or even your advanced developer, though, there's a whole new world if you're thinking about robotics or physical AI called functional safety.

25:23So FUSA. And so this is, anyone who's been working in the automotive industry knows this really well. Right. It's around for quite some time. Right. Don't run over people. Right. Don't run over people. But also your software has to be deterministic. And this is a new, and so this is not just typical safety stuff. This is you even turn off the optimizations and compilers when you're creating functional safety software because optimizations are not necessarily reliably predictable. And so maybe if there's anything to take away from this talk is if you're thinking about robotics, cross-device systems, physical AI, go learn about what functional safety is.

26:00Because there's a whole slew of standards and a whole slew of things that you need to do. And they're really important. Because if we're going to have big, heavy, strong, fast devices flying, moving around, we don't want them to hurt people. And so this is a super important space to understand. And then making those deterministic where most of our AI things are not. That is, yes. That's the problem, isn't it? How do we make something deterministic that's inherently non-deterministic? And the ways you do that, again, you go do the research, you actually split capabilities. So sensing and thinking, thinking and deciding, you kind of segment and split those up.

26:39You really think through fallbacks, right? So this decision needs to return in 10 milliseconds reliably every single time because 10 milliseconds might be what is required to avoid hitting something. And so if your model can't return, you need to know it can or can't return within those 10 milliseconds, you need a fallback that actually can make a decision, right? Or you need to be able to say autopilot's off. So these are the things that we really have to take very seriously. And by the way, the industry is. Yeah. Oh, sure. But there's a lot of learning. There's a lot to do. Yeah. I mean, if there's any societal guardrail, it is the threat of lawsuits.

27:15Fair. Fair. We definitely take safety and security seriously. Yeah. But I think as a company, we really do think we need to be careful with this sort of alarmism. Right? And so we're kind of really encouraging the industry to sort of take policing itself quite seriously. And I think we are of the opinion of other countries are not going to wait. They're not going to slow down. And so this is an area, I think, again, to developers at large, if we all take this seriously and we all kind of come up to speed on this, I think we can continue to move at pace and we can build in the kind of safety and security concerns that are very, very real.

27:56Yeah. But I don't think it's a sort of government legislation and a slowdown that's required. I actually think it's an investment in these spaces. And by the way, that comes, we're the ones writing the software. Right. We're the ones managing the agents. Like, I think we, it's kind of in our power to take this stuff seriously. And so I think we can do it if we combine it. Yeah. I mean, you know, AI in a lot of these, these sort of publicized breaches, it's just that AI is a goal seeking machine, right? You give it a goal and they'll figure out how to do it. Correct. For robotics, do you think the sort of separation of concerns FUSA is enough to stop the universal paperclips machine, right?

28:37I am a believer in the benefit that AI can provide. And we will have bumps, for sure. I think it is. But we've had these powerful technologies before. And we make mistakes along the way. But this is one of the reasons I love the industry. I love developers. We're problem solvers, right? Inherently, that's what we do. And this is where humans have to take their own responsibility and why we're not going to cede all the decision making to the robots. And so I think it's something we can get behind. And again, I'm pushing this because we're the developers. We're the ones kind of, we see the quality tests.

29:18We see the gates. We're the ones building these protections in. And so it's in our hands. I think we can do it. I hope people do, in fact, take responsibility.

29:31Well, I have been Ryan Donovan. I hope you've enjoyed the conversation. I am the editor of the blog, host of the podcast here at Stack Overflow. So if you like what you heard, please leave a rating and review on your favorite podcast provider. And if you want to reach out to me directly, contact me directly. You can find me on LinkedIn. I am Alex Spinelli. I'm the Senior Vice President of AI and Developer Platforms at Arm. And yeah, I am available on LinkedIn as well. All right. Thank you for listening, everyone. And we'll talk to you next time.

30:08Thank you.

From the publisher

Ryan sits down with Alex Spinelli, Senior Vice President of AI and Developer Platforms at Arm, for a conversation about bringing ML capabilities to edge devices, adapting software tools to meet the unique demands of autonomous agents, and the critical importance of prioritizing functional safety as artificial intelligence transitions into the physical world of robotics.

Episode notes:

The new era of Arm is focused on maximizing performance and power efficiency for AI workloads across edge devices and cloud infrastructure.

Connect with Alex Spinelli on LinkedIn.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

More from The Stack Overflow Podcast

All episodes