Advantest Talks Semi

Adding Context: Helping AI Learn the Language of Semiconductors

• Don Ong • Season 3 • Episode 7

Share episode

Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.

0:00 | 42:48

From fusing wafer maps and test logs to powering lights-out factories, Contextual AI offers grounded, secure, and context-aware intelligence to make testing more efficient. 

Thanks for tuning in to "Advantest Talks Semi"!

If you enjoyed this episode, we'd love to hear from you! Please take a moment to leave a rating on Apple Podcast. Your feedback helps us improve and reach new listeners.

Don't forget to subscribe and share with your friends. We appreciate your support!

SPEAKER_01:

Hello and welcome back to AvanTest Talk Semi, where we dive deep into the technologies and ideas that are shaping the world of semiconductors. Today we're exploring a question that goes beyond silicon. What if AI could truly understand the language of semiconductors? To help us unpack all this, we're joined by Dow, the CEO and co-founder from Contexture AI, the pioneer behind the unified context layer for enterprise AI. Unlike generic large language models that often stumble over technical jargons and high-stakes data, Contextual's AI approach is designed to fuse structured and unstructured information, ground its reasoning in facts, and minimize costly errors. In an industry where a single wrong decision could scrap a wafer worth millions of dollars, this is a game changer. Looking ahead to LightSouth Factory and knowledge-driven digital tweens, contextual intelligence might just be the missing piece that makes all this possible. So in this episode, we'll explore how specialized AI can number one speak the language of Fab testers and EDA's tools, how it fuse wafer maps, test logs, and design documents into meaningful insights, prevent error snowballing in high-stakes production, and also enable a secured, trusted path towards fully automated semiconductor factories. So let's welcome Dow. Hi everyone. Alright, Dow. So you know, when we think about semiconductors, the language itself can be a real barrier. Acronyms, beaning codes, wafer slot locks, it's almost a dialect that only insider speaks. But generic AI models, they often misinterpret or even hallucinate. Imagine if we had AI that truly spoke the language of semiconductors. So, Dow, why do generic LLMs struggle so much with semiconductor jargons and acronyms? Can you share an example where this gap becomes critical in practice?

SPEAKER_00:

Yeah, it's a good observation, right? Not every field is the same. I I think uh semiconductors is is is a pretty unique domain in that uh there's a lot of sensitivity around intellectual property. Uh so that means that a lot of that that data hasn't been seen necessarily by language models, which which makes it harder. Uh, and like you said, there's there's just a lot of unique language uh to it. And and uh you know, as a as a generally trained, non-specialized language model, it's very easy to get confused by very simple terms. So if you think about like what's the meaning of EDA or SLT or sort of basic terms that everybody in the field knows, um for an AI model that can mean many different things. Um so um yeah, it's uh I I think a really nice example of a very specific domain where you care a lot about accuracy, you care a lot about having things work on very large-scale, very complex data and solving very complex, highly valuable problems, and then doing that in a way where you can protect um sort of the privacy and and the underlying IP and make sure that uh that doesn't leak.

SPEAKER_01:

What are the real-world consequences if an AI misinterpreted terminology in our industry, for example, in geoanalysis or test engineering?

SPEAKER_00:

Yeah, uh a small mistake can be very expensive, right? If you uh I don't know, if you uh give a wrong answer for the voltage on uh pin seven and uh you know uh something goes wrong and and fries, uh that could have have massive consequences. So um hallucination is a very big problem in general uh with language models, and and that's one of the things that we are really focused on removing from these AI systems. Um but yeah, I I I think in in semis, it's just a a mistake can be incredibly costly and you have a very, very low tolerance for hallucination. Um, and that's why you need to be extra careful with the AI systems that you that you build yourself or or that you build with others and make sure that you have the right guardrails in in place uh so that you can avoid those costly mistakes.

SPEAKER_01:

Yeah, exactly. So it if we get a false positive down the semiconductor value chain, we end up with a very expensive product that doesn't work. So that's something we want to avoid. So let me move a little bit into the technology that you guys have. So, how does your context engineering approach actually teach AI to understand semiconductor specific language rather than just memorizing terms?

SPEAKER_00:

Yeah, so so one of the core concepts in in AI that maybe if if people have been looking into AI that they might have heard of is something called RAG, retrieval augmented generation. Right? So my claim to fame originally as an AI researcher uh is that I'm one of the co-authors of the RAG paper. So I I worked with my team at at Facebook AI Research at the time on making this possible. And the idea of RAG is actually very simple. It's how do I connect a language model, a generator, to data in a way where I can use information from that data to uh give the right answer, right? So um over time, I I think RAG has emerged into something much more powerful than than when we originally introduced the idea. And it's really about having so much data like you do in in semiconductors or or mostly uh in any large enterprise, you have way too much data, right? And it's all over the place, it's very noisy, it it um it's a mess, right? And everybody will will agree that it's a mess. So then the real problem that we have right now when it comes to getting value from Gen AI is how can I get the right context from all of that data to give to a language model or an agent so that it can solve a valuable problem for me. And that could be a very simple thing, answer a technical question. It could be a very difficult problem like generate a test program or um you know um uh analyze a log file and give me the root cause of what went wrong with this kind of device here. So so there's all kinds of things you can do. The the common problem that we have is how get how do you get the right context from the data to solve the problem.

SPEAKER_01:

Do you see semiconductor manufacturing as a proving ground for domain-specific AI? Could the lesson learned here be applied to other complex technical industries like aerospace or biotech?

SPEAKER_00:

Yeah, totally. I believe so. I I do think that semi semiconductors is uniquely suited for this. Um, but but I I think uh in general there is this uh problem of making general systems work on specialized problems, right? And if these general systems are really meant to work for everybody, like a standard like ChatGPT, it's amazing, right? It's an amazing piece of software, but it is meant to serve everybody, uh, which means that you know it needs to be able to brainstorm creative stories with the marketing department when you're doing creative writing. And so that type of hallucination, maybe if you want to call it that, is really something you don't want to have when you have a sensitive domain like like semiconductors or aerospace, like you said. So different domains have different kinds of trade-offs, and that's why you don't want to have a generic model that works for everybody. You want to have a specialized model that understands your jargon, that works on your data, that um understands things slightly more deeply, just in the same way that you know, if you want to get into semiconductors, you need to go to school for that. You can't just go and and just you know walk into a place and and expect to understand the conversation. Um so yeah, specialization is is pretty important. Totally, totally, totally agree.

SPEAKER_01:

And uh I'd like to dive a little bit deeper into the structured and structured and unstructured data that you just mentioned, right? So in semiconductor, data is not just big, it's messy. We have a lot of different players in throughout the entire semiconductor value chain. So we've got structured data like NES logs, uh the SPC charts and yield dashboards, and that's structured. But for unstructured, we have like engineering notes, PDFs, design documents. So the challenge for us has never been storing it, but it's about connecting the dots across all these silos. So, Dow, why is it so difficult to connect structured data like NES logs and with unstructured sources such as engineering reports or design nodes?

SPEAKER_00:

Everything is about context, right? So if you want to understand unstructured documents, then you probably have to understand them with relation to maybe some things that are in the database somewhere, or or like you said, device logs, or maybe you can understand the logs better if you understand the manual of the the chip that you're sort of analyzing, right? So there's there's all of these interdependencies across different data sources, and different data sources have different data formats. So uh the way to resolve those dependencies is by by having very good contextual understanding. Um and the hard part when you think about how do you analyze a big log. Like let's say you have gigabytes of logs uh somewhere, and um, as a human, what you would have to do is basically kind of scroll through it, or you would maybe control F for like fail or error or something like that, and then you would read the logs, right? So um an AI system can do a very, very similar thing. And what used to be very hard was that we had what we call text as equal, right? Or so or or sort of like basic like lexical search over log files, and then we have embedding-based search, which means that you can get the semantic information out of unstructured data. And it was very hard to figure out which do I use when and how do I combine the results out of all of these different data sources. So in modern RAG pipelines, we have things like re-rankers. Maybe you've heard of that. So you do an initial retrieval step from all the different data sources, and then you use a re-ranker on top of the initial retrieval results to find the final pieces of information that you want to give as context to the language model. And when you have a good re-ranker, like we do, uh, we have probably the best re-ranker in the world that can follow instructions as well. So you can give it very specific uh contextual knowledge that it uses to find the right pieces of information, uh, then you can really uh solve very, very hard problems.

SPEAKER_01:

When you talk about re-ranker across structured and unstructured data, so how does that differs or or does that matter at all?

SPEAKER_00:

Yeah, so so uh every piece of data is different, um, right? So so um um that that's why you need to have a re-ranker that can make sense of all of these different data types and also understand uh what we call the metadata basically. So the source of the underlying data, does this come from a device log? Does this come from a database? Which database does it come from? Like all of that information is is important when you have to figure out what the right context is. Um and and so with this new world of, I'm sure everybody's heard about agents, right? Like agents are are really the future, and and so what agents can do is is use tools to do retrieval steps. So you can actually when you do an initial search and you find some promising uh results, but maybe you want to get some more information as an agent, it can just go and look for for other agent elsewhere. So it's really a very similar process to how you would tackle this as a human, but then much, much faster, much more efficient, and you don't have to do it, right? AI does it for you. So so like device log analysis, I think, is a great example where in some cases companies we work with they can take days to analyze a log file just because of of its sheer size, and they need to like cross-reference. Maybe they need to call somebody to get some more information. It's like what if you could just solve that in five minutes? Uh that's massive time saved. Um, so there's a lot of potential for for AI uh across the sector.

SPEAKER_01:

All right, totally agree. We we need to get all capture and use all this unstructured data today, where which we're not using it today, right? So um I'd like to move a little bit forward. So if we take wafer level failure and want to trace it to the assembly logs, line logs, so how does contacts AI approach help engineer discover that connection faster?

SPEAKER_00:

Yeah, I mean, uh, so that's really a reasoning problem, right? So so this is what agents are amazing at. And and obviously, like a just an out-of-the-box agent is probably not going to be great at at solving a problem as specific as that one. But if you specialize the agent and if you inject all of this contextual understanding and if you make it sort of see the broader context of of kind of the the process that that you're trying to analyze, then you can reason backwards. Um, and and so uh this will help you uh optimize uh processes like this and really identify the boot cause that might be causing a failure or whatever you're trying to analyze. Um so so what it's really about kind of um compounding performance in the end with these systems, right? It's like you know you have all of these different kind of like small decisions that you need to make, and they're they're like sub-agents kind of working together, analyzing different parts maybe of a supply chain or something. And and if they all work together, then you can really just um optimize the entire chain, and and that leads to to massive value.

SPEAKER_01:

So it's interesting you talk about agents as well, because as we implement more AI agents along the way, people start to think about does do you have a job? And then we start talking about human in the loop automations. So our engineers often jump between dashboards, PDFs, emails just to make sense of, you know, if there's an issue. But how do you see AI reducing that friction, but keeping human in control of critical decisions?

SPEAKER_00:

Yeah, it's extremely important to keep the human in the loop, especially in in uh in a high-stakes settings, the setting like like the one you described. I I think in in in your sector, it's really important that you are not just going to hand over the keys to AI and say go run with it and like you know, design something cool and we'll we'll just manufacture it at scale. Like that would be very uh expensive mistakes, I think. So um, so you need to have humans in the loop and you need to figure out when you when you want to put them in the loop. So the promise of AI, I think in some sectors it might replace people's jobs. I think in more specialized sectors, it is going to augment the people uh in those sectors already, right? So think of think of like a customer engineer at like a large semiconductor company. So all the work that they're doing, there's actually a lot of work that doesn't necessarily require a lot of like deep skill or expertise or intelligence. It's kind of just mundane, right? Like you said, basically, like checking some emails and reading some files and maybe scrolling through a log and like all of that is kind of like boring, boring stuff that you have to do to solve the problem, right? So if AI can do that for you, think of all the the productivity gains that you get from that, right? You can just deliver a lot more value as an expert in the field by having kind of an AI sidekick that augments you and and does all the boring stuff and all the plumbing for you. And that that sounds pretty wonderful, I think.

SPEAKER_01:

Yeah, that's why we call operational efficiency, right? We get more, our employees get more and more efficient, and then we get more and more productivity. So as we move forward on this, uh, the key trend right now is talking about lights out factory, where there's no humans in the factory floor, and also digital tween, some people call it knowledge tween. How do you see this uh fusion of structured and unstructured data as a step towards creating a true digital tween of the fab, you know, something that could eventually drive real-time decision making in LightSouth Factory?

SPEAKER_00:

Yeah, so so so I I think um with these types of complex processes, which that obviously is, right? That is not a trivial task. Uh, that just requires a very, very broad set of data sources that you need to reason over. And a lot of these are structured, a lot of these are unstructured. Um and and so um I I do do believe that that we are going in this direction where you can just automate a lot of these processes uh in very clean ways, as long as as as we discussed, you you identify the spots where you want to have humans in the loop. Um, but yeah, it's it is really about understanding the contextual pieces of all these different uh uh data sources that you need to work over, right? It's like understanding sort of the physical world that you're in, and then understanding kind of the the sort of um uh the problems you're trying to solve, understanding the processes that you have, the unique intellectual property that goes into uh this those processes. So all of that that context needs to come together. Um, and that's uh that's a hard problem.

SPEAKER_01:

And and I really like the way how you structure this. So we could have human interloop in where we design where we want human interloop, kind of like a control point, a control tower. And then the rest of the stuff uh that can be automated will have AI robots, AI agents with REG that talks to each other and understand each other from a context perspective and do a lot of automation, right?

SPEAKER_00:

I I have a nice example there, actually. Maybe so we work with a lot of like finance customers too. It's actually surprisingly similar in a way, right? This complex domain, sensitive about IP, lots of data that is sort of all over the place, and you want to solve like complex problems on top. And so one of the big problems they have is that they have very noisy, large documents that they want to understand uh in a kind of structured way. So they basically want to extract, let's say, 10 different fields from a large report. It's like what's the company's name, what is their revenue, what is their projected revenue, or something like that. So one of the things that we do in those use cases is we extract the information, we're very good at kind of document understanding, but then as a part of the extraction, we also assign a confidence score. Um, so that means that if the system isn't really sure, you probably want to have a human in the loop. If the system is like 100% sure, like the revenue was X, you probably don't have to double check it, right? But maybe if it's like, well, I'm kind of 50-50 because there are like two different tables and they sort of report different numbers for different time periods. Is that this is something that as a human you want to double check? So then you can build that into your your flows as well to make sure that whenever AI sort of self-identifies that it's not quite sure about the answer, then that's where you call in the humans. Um, and I think that yeah, those those kind of processes are are becoming pretty well established at this point.

SPEAKER_01:

Let's talk about the cause of errors and how it propagates. In semiconductor and you know, in cheap design, precision isn't optional, it's survival. A single wrong insight could mean scrapping wafer worth millions of dollars or misdirecting our engineers to the wrong root causes. And unlike other industries, error here doesn't just add up, they snowball. Uh, that's why zero defect expectations and adaptive testing put such high demand on AI systems. So, so Dao, why is error propagation so uniquely costly in the world of semiconductor compared to other industries?

SPEAKER_00:

I mean, I honestly that's a question for you to answer. Like you're you're the semiconductor expert, I'm the AI expert, right? But I I think it's it's a very, very uh good observation. I I think uh especially when you have sort of very, very complex processes with lots of interdependent steps, like one small mistake in the beginning at the end can have huge repercussions. Um and and so for for us, actually, in AI, um it is is is similar in a way. So the the accuracy of the overall system is dependent on all the individual AI model components that exist in that system. So if you think about RAG, retrieval augmented generation, you usually have some sort of document extraction that you do first, so that you can store the information in a vector database, so you encode it with embeddings, and then you do retrieval, and then you do re-ranking, and then you do generation, and then maybe post-processing or guardrails. So you have lots of different steps. And so if you're in a domain like semiconductors and 1% of accuracy in the final answer can have huge repercussions down the line, then you really want to make sure that all of these parts are optimized so that you get the max possible performance. And and just like in the semis and and sort of the supply chain there, in AI, all of these dependencies compact. So if you have a very bad extraction system, your retrieval is not going to be very good. If your retrieval is not very good, then you can re-rank the results, but it's not going to give you the right result, which means that you give the wrong context to a language model so you can have an amazing language model, but it will still not be able to get the right answer because it doesn't have the right context. Um, so you see the dissimilar kind of snowballing uh happening in AI systems kind of across the board.

SPEAKER_01:

Exactly, exactly. And and that's why in semiconductor is so important for us to get proper testing done and get accurate results. So we prevent false positive de facto going into the next step, which just costs us a lot of money just to scrap it later. But um, so in AI, as you mentioned, which is the same, right? You when you have an error, it's just if you let an error go into the AI system, the LM system, that's just going to snowball because it understands things differently and it's going to make different suggestions, uh, maybe a wrong suggestion in that sense. But those so how does contextual How does AI prevent this snowball effect? How do you catch the error when you're trying to digest a document or you digest an NES log? How do you prevent this error from snowballing? And especially when you know our engineers really rely on outputs for adapted test strategies.

SPEAKER_00:

I feel like it's in a way pretty similar to your industry. So we do a lot of testing. I mean, uh, I'm sure you uh agree with me that testing is important. You really want to understand the performance of each of the individual components and you want to think about it holistically. Right? So one of the things that we often see a lot of our competitors do wrong, or that we see some of our uh you know, folks in in the field before they come to us, the mistakes they make, they're they're very often about thinking about it from a single model perspective. It's like, oh, I have like a language model and I have like a retrieval model or something, right? Rather than thinking about it holistically, saying I have this problem I want to solve, and I need to have a whole system that optimizes against solving that problem. Uh, and so when you take this systems approach, um then then you can just have have much better performance because you account for that kind of compounding over time, right? Or the cascading of errors, uh, if you think about it that way. So that's something that we take a lot of pride in, is really systems over models, as we call it, and then specializing those systems so that you can solve hard problems. Very true.

SPEAKER_01:

So we talk about zero de facto expectation, and and for semiconductor, that is very important for us. So, in in in your mind, how realistic is it for AI to support that kind of mindset for a zero de facto without over compromising?

SPEAKER_00:

Yeah, so for AI on its own, I would say there is a zero percent chance of that being uh a realistic uh goal. And and so so that's why humans in the loop are important and why you need to have specialists like double check results and and just verify uh that things are correct. So AI can handle a lot, but one of the the the big things about AI is that you know it's a it's it can hallucinate and it makes mistakes, just like normal humans sometimes make mistakes, right? So if I go back again to like finance as an example where it's a different sector but sort of similar problems, there are very good guardrails in place when it comes to the behavior of the bank that come from regulators like the SEC or folks like that who say, like, this is your process that you have to follow, where humans need to kind of sign off on different things to make sure that something is actually correct, right? Because otherwise, like our global financial system is at risk or something like that. So, in those types of of kind of decision uh trees, there have to be double checks and humans. So some of the parts can be AI, but you probably want to keep humans in the loop there and then make sure that you leverage AI in a way where if the AI is not sure, then you call in the human, right? Or sometimes you can have AI double check the human. So it it's very symbiotic, I think, in in in the future, uh, when it comes to um solving high-stakes use cases, and we will be working together with AI, but letting AI on its own do it, I think is is still a bit of a pipe dream.

SPEAKER_01:

So I want to touch on a point that you make slightly earlier to talk about, you know, uh AI is going to take over some jobs and uh that is maybe lower skilled and not so much for jobs that are higher skilled. In the semiconductor world, as we do testing, especially for advanced tests, which do a uh we sell task equipments, so we do a lot of testings. Do you see contextual AI as an enabler for a new form of adaptive testing? So where AI not only analyzes results and helps engineers make decisions, but it also helps dynamically optimize our task programs in real time so you you get your task programs get smarter and shorter and more efficient.

SPEAKER_00:

Absolutely. I I think that that's sort of the the the promise of AI here, right? It's like like we already talked about like context matters, and and the more of that contextual understanding you have, the more you can really tailor things. So if you have to design a very specific test program for what you care about, AI can help you with that. As long as you can provide the right context and the right instructions for what you're looking for, um, and maybe even set up a feedback loop, right, where over time it actually gets better and really like adjusts to you, maybe even like individually as a developer, like what you care about. You can really start to do that when you have that contextual understanding. So I think there's a ton of promise for um yeah, taking uh kind of advanced testing to the the next level.

SPEAKER_01:

So I like to move forward into lights out factory. I think a lot of our our audience and and for us, we think that's the future as well. So a lot of our customers are working on this. Um, think about in a lights out factory when there is no humans, but there's a ton of a lot of different machines in in the lights out factory, and they need to talk to each other to understand each other so they can work together. So the dream of a fully automated lab or a true lights out factory, you know, it's been on the horizon for years. We talk about that, and there are some people who started working on that. So we need robots, we need sensors, we need MES systems that really power parts of this vision, but something is still missing. It's a brain that can orchestrate it all. I think this is where context or where AI comes in, is not just retrieving data, but understanding, reasoning, acting as a trusted digital tween of factory knowledge. So, Dow, when people talk about lights out factory, what do you think is the hype and what's possible, actually possible today in in the in the semiconductor fabs and task floor if we use contexture and contact can contexture AI be that brain for our likes out factory?

SPEAKER_00:

I would like to say yes, but I I guess we have to show that in practice. Right? But uh so yeah, I I I think what's so interesting about that is is just that it's a very complicated um uh process with so many different interdependencies, and like we've been talking about, right, there are lots of opportunities for cascading errors there. So um I think it's a really good test bed for thinking about this future of multi-agent systems, right? So that's really one of the big things that a lot of us are in AI are are really excited about, is it's not going to be just one agent, one Chat GPT or whatever that solves your problem. It will be lots of different agents, and they're all specialized in in very, very different ways. They have their own context and their own sort of personalization, each of them. And then to your point, it's really a question of how do you combine all of that and how do you make that work together and how do you jointly optimize that as sort of a system of systems, maybe. Um and and um, yeah, I I I think um it's a matter of time before we we can do that. I think from the AI perspective, we're basically there, right? I think one of the harder problems is actually just like physical uh intelligence, so robotics that actually have have like fine-grained enough control to do what they need to do uh in a robust way. And so I I I think um 10 years ago, probably a lot of folks would have expected robotics to be much easier and language to be much harder, uh, but it turns out to be uh the opposite. Totally agree.

SPEAKER_01:

So as you mentioned, we talk about, right? Um, it's about having multiple AI agents working together, and then now we're just waiting for kind of waiting for the robots to catch up. But how does contextual AI function as a trusted digital tween of factory knowledge base? You know, it's not about working with all these AI agents, multiple AI agents, to get this knowledge or to get this data from them and then understand that, combine that together, having and then having them talk to each other. Um, is is contextual AI uh helping in that sense?

SPEAKER_00:

So the the talking to each other, I think is a very open research problem for a lot of folks in AI, right? It's like um I think in many cases uh it makes sense to talk to each other in natural language, because then you know a human can always jump in and double check whether whether what the agents are talking to each other about makes sense. But for machines, language is very inefficient, right? It's like or at least natural language that we speak, whether it's English or Chinese or whatever, is extremely inefficient when you think about it from a computer's perspective, where maybe you just want to send code or like raw data, right? Um, but then you sacrifice interpretability. And I think one of the big um things that we care about in in these very complex multi-agent systems is interpretability. Uh so we need to make sure that we can observe what's happening in the process and always kind of interject uh human oversight. Um so so uh you know, that's why it will probably be some some version of some language that we can understand.

SPEAKER_01:

I like to pick your brain a little bit. So let's move forward five to ten years from now. If if you can imagine that we have a semiconductor fab or OSART uh task that is fully automated and contextual AI is embedded as this decision-making layer, how do you envision that? How do you see that happening and and what else is missing? What else is required to make this happen, to make contextual AI as part of that decision-making layer?

SPEAKER_00:

I I honestly think that that in terms of pure technology, everything is there uh outside of the sort of the robotics, physical intelligence side of things, and and maybe sort of some of the processes around it, or even like regulatory processes and and sort of um maybe some of the like change management and and you know a lot of the vaguer things. I I think one of the the exciting uh things about where we are right now in time is that we had this core capability of of intelligence, and then we are starting to really solve this problem of context. So now we can give the intelligence the context that it needs, um, and and you know, so that these intelligences or agents can also work together. Um, and then um the the real real question now, and that goes goes, I think, much much further than than the fab. It basically extends to the whole world, is how how does this manifest itself? Like what how does this become a product, right? It's like how do we productize AI? Um, and and I think um we're going to find out in the next uh uh five years what it will really look like and and so um how much human involvement there will be, um, you know, how we are going to make sure we can rely on these systems uh and uh how can we make sure that they don't kill us and and that kind of kind of stuff. Uh so so some very, very deep, profound questions uh that we need to uh solve as a society in the next few years.

SPEAKER_01:

Yeah, yeah. And and you know, also personally, uh as we're implementing AI as well, I think having um more AI in our processes, in our workflow, in our factories, uh, that also gives us a chance to redesign our processes and also redesign the workflows, redesign a lot of things that we can make it easier for and and it's not possible because uh we don't have that technology. Now AI comes in with a lot of automation, a lot of understanding, and just enabling that for us to change. And so I think besides just technology change, a lot of processes, SOP workflows, and how we design our machines is gonna change. What do you think about that?

SPEAKER_00:

The change is coming, managing the change, so change management, that's really the big challenge, I think. Um and and you know, like you mentioned SOPs and and sort of like basic things that feel basic to humans, like a like a machine could just like mix up the order of the SOP and like you know, in a way they're like incredibly smart, but at the same time, they're incredibly dumb. Um and and where they are very dumb is often when it comes to this this kind of context problem. Um so so that's why um when we solve that, uh it's going to unlock a lot of very exciting things.

SPEAKER_01:

In semiconductor data isn't just valuable, it's extremely important. So design files, Tesla, guild data are crowned jewels in our industries, and protecting them is non-negotiable. Uh, that's why any AI system that we use must deliver insights without ever putting any IP at risk. So, Dow, why is data security, IP protection such a unique concern, you know, uh when we come when it comes to adopting AI systems?

SPEAKER_00:

Yeah, it's an incredibly important problem. Uh, and I I think there are are so there are lots of sectors that have this problem. Like you said, finance is very similar, right? It's it's in the end, actually, when you when you think about what the future looks like, what makes a company unique or what makes a company a company is its data and its expertise and its intellectual property, right? So beyond like in the future, maybe there there might be like three people working at at JP Morgan, and the rest is all AI, right? Uh like I don't know if that's a real uh good example, but uh you get my point, right? It's like people uh make a company right now, but in the future, if if you extrapolate, data makes the company. Um, and um uh you have to be extremely careful with that data. And one of the worst things you can probably do right now is give all that data to OpenAI or Anthropic so that they can train on your data and then uh solve all these problems in the future, right? So that's one of the things that we we focused on when we started the company. We knew that RAG is really a way where you can give language models this information without the language models training on it. Um so our entire system is deployable um inside the customer's VPC, which means that no data ever leaves your security perimeter. Everything stays inside, it doesn't get leaked so that your competitor also benefits from um from the the work that you put in. Um so we think that's very important and one of the the things we do differently from a lot of our competitors.

SPEAKER_01:

Yeah, yeah. Like you mentioned, I totally agree that you know we don't want to share our design data with open AI or other large language models so that they can build a better tester than we do. So it's same, yeah. So so same thing. Um or that your competitor can use open AI to build a data. Yeah, and then build a better machine that's better than Avan Test. We don't want that to happen. Um, so as you talk about RAG contextual AI, you know, being able to extract the data and keeping it keeping all our sensitive data within our secure uh parameters, how do we know RAG like contextual AI is not learning from us as well?

SPEAKER_00:

Yeah, so so the system gets deployed in your data center. So we don't even see the data. Right? So so it's really your deployment there, and and that's really uh I think important is that you control what data goes into VAF and you control kind of the artifacts that are created as a part of that system.

SPEAKER_01:

So, what about going across companies, going across uh different companies right now along the semiconductor value chain? So, because we start to see that there is a need to share information. So the question becomes how can I share information with my customer, with my vendor, but not losing my IP? So, and and I suspect RAG and contextual AI could be a way of doing that. So, can you talk a little bit about that?

SPEAKER_00:

Yeah, so I mean there are different ways to do that, right? I I think honestly a lot of us more broadly are trying to figure out kind of like where where do these data handoffs happen, right? If you if you think about like all the different like file storage providers from your like Dropbox to like your SharePoint or something, it's like where like who owns the data and who owns the context that comes out of that data. I I think that's still a lot of people are figuring that out, right? Like Slack and Salesforce, they've actually tried to lock it down so that it's not possible to do your own search on it. You have to use their search. Um, so there are there are good protocols like MCP and A2A uh that are getting developed now in AI when it comes to making different data accessible to different uh parties, right? So maybe in the future for for some of your like internal manuals at at FNTS, you might have an MCP server that is powered by contextual AI that has all of your manuals so that if one of your customers wants to ask a question uh on a manual inside their AI system, then they can just very quickly call uh the MCP server and get the right answer with the right attributions. Um so yeah, we're we're still figuring that out, but I think that's one of the key benefits of having context as kind of the connective tissue between intelligence and data, right? If you wanted to take all the data and just train the intelligence on it so that it knew everything, then you could never really solve that problem. So uh the only way to really do that is with RAG and context engineering.

SPEAKER_01:

We've heard a lot from Dow and thank you very much for joining us. So before we end this, can I just ask you one last insight that you have for our audience, for our guests, for in this in the semiconductor? How can contextual AI, how do you envision contextual AI in the next five years for the world of semiconductor?

SPEAKER_00:

Yeah, I think we we are extremely excited about semiconductor as a sector and the potential that it has. Uh, it's extremely contextual as a domain. Um, so you need contextual AI to make it work. And um, yeah, I I think the the real interesting problem with AI is about delivering real-world value. And that means not solving the easy problems, right? Like we used to have AI demos, and then you could ask it, like, how many vacation days do I get? It's like, okay, sure, like AI can answer that, but that's not valuable, right? Like you could do that before already, and it's it doesn't really add value. But if you can actually do some of the things we talked about in this podcast, if you can really do that with AI, that is so much value that we're adding to society. Um uh, you know, the so we're we we live in very exciting times. So, sort of my my my parting thought, I guess, for for folks listening in is really try to be ambitious and and think about what you are going to be able to do in the next couple of years, and and don't settle for the boring, easy use cases and like you know, basic question answering on some documents or vacation days or things like that. Like try to solve really, really hard, valuable problems where you have high enough accuracy that you can actually put this in front of your own customers and and uh and rely on AI uh doing a good job. So we're we're heading there. Uh it's gonna happen in the next few years. So it's exciting times.

SPEAKER_01:

Exciting, exciting. I love that. And and it's extremely important that uh when we do AI, we think about actual and real ROI, and that's why it matters. Well, today we have seen how the semiconductor industries provide one of the toughest, most fascinating task beds for AI. From teaching machines the language of semiconductors to bridging structure and yes logs with unstructured design nodes to avoiding costly error snowballing, the idea of a unified context layer shows us a path forward. Uh, we've also explored how context-aware AI could serve as the brain of future lights out factories and how all this innovation must be built on the foundation of trust, security, and data ownership. It's clear that semiconductors don't just need more data or faster model, they need contextual intelligence. Uh, that is exactly what contextual AI is bringing to the table. So a big thank you to Dow for from Contextual AI for joining us and sharing all these insights. And a big thank you for our listeners for tuning in to Advanced Talk Semi. And I look forward to seeing you in the next episode. Thank you for having me. Thank you.

Head Shot

Don Ong - Director and Head of Innovation for the Advantest Field Service Business Group.

Host
Head Shot

Keith Schaub - Vice President of Technology and Strategy at Advantest

Host
Head Shot

Learn more about Advantest

Host