DeepMind's New AI Just Cracked The Code Of Life

Author: Two Minute Papers · Watch on YouTube

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: DeepMind’s New AI Just Cracked The Code Of Life · Channel: Two Minute Papers · 32:56 · Watch on YouTube

Topics: AI models, Health and science

Summary

The video introduces AlphaGenome, a DeepMind model that predicts how genetic variations affect molecular processes such as gene expression and splicing. Its key advance is combining base-pair-level resolution with a large genomic context window, and it performs strongly across variant-effect benchmarks. AlphaGenome Atlas precomputes predictions for billions of possible single-nucleotide variations and makes this large dataset available to researchers. The interview also discusses the model’s limits, the need to validate predictions experimentally, and future ambitions such as modeling cells and using AI to advance biology and other sciences.

Key points

AlphaGenome predicts the molecular effects of changes in DNA, including effects on gene expression and splicing.
The genome contains both protein-coding instructions and non-coding regulatory information; the latter is less well understood.
Many traits and disease risks are polygenic, involving multiple genetic variations, so molecular predictions still need to be connected to organism-level outcomes.
Training on both human and mouse genomes can encourage the model to learn principles that generalize across species.
Unlike earlier approaches described in the interview, AlphaGenome combines base-pair resolution with a large context window to account for effects that may occur far from a variant.
The model matched or surpassed the strongest comparison model in 25 of 26 variant-effect benchmarks, according to the interview.
AlphaGenome Atlas precomputes predictions for possible single-nucleotide variations, creating a petabyte-scale resource for the scientific community.
The interview describes the AVI score as a way to help researchers prioritize variants for closer analysis.
Predictions are tested in the lab, but the team is still investigating how the model represents and learns biological mechanisms.
Future directions include improving context awareness, connecting molecular effects to organism-level outcomes, and exploring applications in synthetic biology.

Chapters

Start	Chapter	Summary
00:00	Introducing AlphaGenome	The interview opens with the promise of understanding cells and introduces AlphaGenome as a model for predicting the effects of genetic variation.
03:42	Individual differences and genetic variation	The speakers discuss how genetic differences may contribute to variation between people and distinguish single mutations from polygenic traits.
06:16	The genome as recipe and instruction manual	Pushmeet explains coding and non-coding DNA, model access for researchers, and how training on human and mouse genomes may improve generalization.
10:27	Resolution, context, and benchmark results	The discussion covers AlphaGenome’s combination of a large context window and base-pair resolution, its benchmark performance, and the team’s evaluation process.
15:10	AlphaGenome Atlas and variant prioritization	The interview explains how the Atlas precomputes predictions for genetic variations and introduces the AVI score for helping researchers assess variants.
19:19	Applications and biological mechanisms	The speakers consider AlphaGenome as a foundational tool for disease research and synthetic biology, and discuss how its predictions are grounded and validated.
24:02	Model representations and next steps	They discuss the simple predictor built on the model’s learned representations and future work on biological context, data, and organism-level effects.
26:39	Gemini, simulations, and scientific learning	Pushmeet describes Gemini creating an interactive wind-tunnel simulation to help explain airflow to his son.
29:16	AI’s potential for science	The interview looks ahead to virtual cells, climate research, new materials, and the possibility of designing biological functions.
32:25	Closing and sponsor message	The host thanks Pushmeet for the conversation before the video closes with a promotional message for Lambda.

Quotes

Alpha Genome is a machine learning model which makes predictions about variation in the genome. — 01:03

What AlphaGenome it tries to do and is the first model to achieve that is to operate at the base pair resolution and have this very large window — 12:03

What Alpha Genome Atlas does, it basically pre-computes all of this. — 16:13

the tasks that it is being asked to solve are grounded in physics. — 23:31

Simulating even a cell. Creating a virtual cell. — 29:16

Concepts and entities

AlphaGenome, AlphaGenome Atlas, AlphaFold, Enformer, Human Genome Project, AVI score, Gemini, Google DeepMind, Pushmeet, Lambda

Full transcript (original language)

00:00 If you can completely, sort of really understand the workings of a cell, that will have amazing consequences for the fight against diseases like cancer. >> I feel like I’ve been dropped into a science fiction movie. Like we we could only dream of of having technology like this when I was a child. Now, I also have a question, and I was thinking that maybe only you can answer this question. >> What Alpha Genome Atlas does, it basically pre-computes all of this. >> Ooh. >> Alpha Genome Atlas is 30 times the size

00:33 of AlphaFold database. >> Wow. >> So, the scale at which uh Alpha Genome uh can produce this the the detailed information about the effect of [clears throat] variation is unprecedented. >> Good to see you, Pushmeet. Look, this is really challenging for me because this is very much outside my field of expertise, if I have any at all. As always, I come here today as a student to learn from you. What is Alpha Genome? >> Alpha Genome is a machine learning model

01:03 which makes predictions about variation in the genome. So, our genome, uh not just the human genome, but uh genome is basically the recipe of life. Uh what it is, it’s essentially a code. In the case of uh humans, it’s a code which has 3 billion characters. And if one of those characters changes, what would be the effect on the actual cell properties? What will

01:36 be the effect on the organism? These are the things that Alpha Genome is trying to sort of uncover. >> And if you’re the person on the street, what could Alpha Genome change eventually about medicine or their life? >> Everyone sort of is affected by uh what happens at the genomics level. Uh the genome is the recipe of life. It has both the ingredient section which says which proteins uh are expressed and the sort of mixing

02:08 section which sort of talks about uh gene regulation, uh when do these proteins get expressed, where do they get expressed, and in what quantity. And all of that information is encoded in this recipe of life. Every single person on the planet has a recipe. I have a recipe, you have a recipe, the person on the street has a recipe. All of our recipes, while they are similar, there are some changes. But what do these changes actually mean?

02:40 What are the implications of these changes? That’s what we have been trying to sort of understand for many, many years, if not decades. With the Human Genome Project, for the first time we were able to read the entire recipe book. At least for one human sort of genome. Uh but now we are trying to figure out how do we decipher it or understand what actually happens. If you make a change in one particular character,

03:11 what are the consequences of it? Will it cause a specific disease? Will it basically be uh connected to high susceptibility for some kind of uh problematic uh issue, like maybe having a high body mass index or having more susceptibility to certain cancers? All of these things are can be decoded in some sense by better understanding of the variations that happen in the genome. >> Mhm.

03:42 That is incredible. And I really wanted to ask this because my problem, every now and then I try to read medical papers. It’s not my field of expertise, but I I’m a student. I just try to learn. >> Yeah. >> And my problem is that whenever I read about, I don’t know, any kind of medicine, my problem is that every person is different. >> Yeah. >> And I go to the barber, and the barber says that he never saw two heads that are the same. >> Yeah. >> And I read a paper on muscle

04:13 hypertrophy, like like bodybuilding paper, how to build muscle. >> Yeah. >> And they have a bunch of people carefully selected, same age, same height, same build. >> Yeah. >> They get the same diet. They do the same training. And one guy gets incredibly muscular. They do the measurements. >> Yeah. >> Some others get a bit of muscle. One poor guy didn’t get any muscle at all. And there was one who I think lost muscle. Like, it’s crazy how how different we are. I’m thinking that that is it

04:44 possible that that we could finally be one step closer to understanding how how everyone is a bit different, and what that means. >> Yeah, exactly. I think so, this understanding or deciphering this code of life, what are the consequences? Sometimes those consequences might not mean anything, right? Like, sometimes the changes are like they are not that material. Sometimes they are very material sort of consequences which are very well understood, right? For example, sickle cell anemia. There is

05:16 one particular sort of mutation which causes sort of sickle cell anemia, and we understand what happens there. But most of the things that sort of you care about these days, uh require are sort of polygenic in the sense that there are multiple sort of mutations that are acting on that are causing that particular incident or that that particular phenomena. And in some sense, what Alpha Genome tries to do is tries to figure out like what happens at

05:46 especially at a single sort of mutation variation level at the molecular sort of phenotypes. Now, how do those molecular phenotypes then get affect the the property of the whole organism? Or in in the case of humans the whole the what the human sort of feels like the susceptibility to specific disease that’s something that will still need to be sort of connected and and research will need to be sort of done on that.

06:16 >> My understanding is that before we dive deeper, AlphaFold is free for all of us forever for non-commercial use. >> Yes, exactly. So for as we have sort of done for many of our scientific models whether it’s AlphaFold 1 AlphaFold 2 AlphaFold genome we have made it accessible to the entire scientific community for academic sort of use for them to sort of use it for their own sort of research, fine-tune it sort of

06:47 and the model weights are available. >> All this true and please explain. The genome is the instruction manual for cells. >> Absolutely. I think there’s the genome as I was saying it’s like a recipe book. It has both the coding part of the genome which is like the ingredients sort of section of the recipe book book which says what are the proteins that will need to be synthesized. So the human proteome has 20,000 proteins. So our our genome

07:17 sort of encodes these 20,000 sort of proteins and there could be variations in those 20,000 proteins. And then there’s a non-coding part which is the which is sort of which ex- looks at how are these proteins sort of mixed? How are these proteins sort of expressed? Where are they expressed? In what quantity? And that part is basically the dark part of the genome which is much less well understood because it sort of talks about the regulation of of genes and protein expression. And so,

07:51 I think what Alpha genome is trying to do is trying to sort of sort of decipher and inform this this whole sort of space. >> Now, I also have a question and I was thinking that maybe only you can answer this question. So, I’m I’m really curious about this. This is trained on human and mouse genomes. >> Yes. >> And what I would love to know is that you train it on the human genome. It has some amount of knowledge and and and quality of of results. Then you

08:22 train it on the mouse genome, too. After that, does it get better at the human part? >> Yeah, and so this I think I mean you have sort of sort of seen this in many different sort of places in machine learning neural networks try to fit to the data. And if you just give it the human data, the neural network has the susceptibility that it can memorize or sort of think about the mechanisms that only

08:54 work in the case of the human genome. But by training it by forcing it forcing the model to explain the same effects in the context of the the mouse genome, we are asking the the model to think broader and think about general sort of principles that can explain both these different types of variations. And that really helps in not only model generalization, but also making the model sort of learn about sort of what

09:26 really matters and what’s really happening at the physiological level sort of in those molecular phenotypes. >> I’ve seen it in another Google DeepMind paper that was the Seema project which played a bunch of video games. And I really found it stunning that you play a video game, you have some score on it, and after playing a bunch of other video games, you get better at this game. I think and it seems like maybe the same phenomenon that that but that sounds like intelligence to me, right? You You apply

09:57 the knowledge from other things to to this thing. >> Yeah, and I think that’s transfer learning in action. Where you are able to extract concepts from things which are related, but are different problems and it helps you become better. Right? So, if you sort of solve your math problems and then solve your physics problems, but just getting better on math helps you get better on physics. >> My understanding is that the big advance here was that previous models were

10:27 either too zoomed in and short-sighted, or they looked from far away, but at a low resolution. Now, this one can do both. >> Yes. >> True or false? >> This is true. So, when we started on this journey of uh going after this extremely ambitious challenge of deciphering the genome, um there were a lot of technical challenges. Uh the our genome, as I just mentioned, is 3 billion sort of uh base

11:00 pairs, ATCG, right? Uh sort of a very long uh sort of sequence. And if you want to understand what is the effect of a particular uh sort of variation, you need to look at a broad uh sort of an expanded uh neighborhood around that uh that variant, because it can affect sort of uh things which are quite far off because of 3D interactions and so on. It’s not that a particular sort of base pair only affects uh what happens in its neighborhood. Like

11:31 it the neighborhood could be very large. So, earlier sort of variations of the model, so we had a model called Enformer, which preceded AlphaGenome, where both the context window uh in which we were looking at uh the neighborhood was a sort of smaller, as well as the resolution at which we were trying to analyze the genome was much coarser. Right? We were not looking at what’s happening at the base pair level. We

12:03 were sort of looking at sort of a a large number of sort of base pairs taken together. And we were not looking at 1 million base pair window, we were looking at a smaller sort of window. What AlphaGenome it tries to do and is the first model to achieve that is to operate at the base pair resolution and have this very large window and and that allows it to not only make sort of prediction that a lot of precision, which require a lot of precision, but

12:34 also sort of make predictions which involve reasoning about a much larger set of things that are happening in the neighborhood of that variant. >> I saw that it is so dominant. It matched or beat the strongest comparison model in 25 out of 26 variant effect benchmarks. I think only of AlphaFold did I hear like this kind of dominance. That is absolutely incredible. Now, what I’d like to ask you, when you saw that it first started working,

13:05 what did it feel like? >> Yeah, so I think one thing that we were we have been working on this problem for a long time. As with many of our scientific challenges, uh it is these are incredibly hard problems um and require innovation in many different things like data and a sort of coming up with the better architecture, coming up with sort of new ideas on training and so forth. When we started seeing these results, we

13:36 knew that we were in a different phase. And part of it was expected because we had done all the hard work of enabling training to happen at that resolution, which had never been sort of done before. But to get it right and to actually show that the original hypothesis that we had gone in with, that if you increase the resolution, if you increase the context window, if you regularize the training properly, then

14:08 neural networks will sort of show show the right results. And so that was really rewarding to see for the whole team. >> Was there a phase of suspicion? Like it it it can’t be right. You know, maybe maybe we we tested on the training set or or something. >> Yeah, so I think this is where we have our team sort of we are very very cautious scientists. So there is a lot of work that the team does on sort of on metrics and evaluation. And so when

14:40 the results came in there is you so you there is a genuine sort of uh sort of expectation that you you’re going to uh check it again to make sure that everything is working properly and these are sort of valid results, but we had a lot of confidence in our metrics that we had set them set them correctly because it was not something that we we have been doing for the last sort of three months. Like it’s it has been a project for the last almost four five years or more. >> What is Alpha Genome Atlas?

15:10 >> So Alpha Genome Atlas is essentially a a sort of a dictionary of what happens when you have variation in the genome. So now I told you about Alpha Genome. And what Alpha Genome does is it looks at um your genome and you can ask it the question if a change this uh base pair or this character in your genome from A to a T or T to a C, what would be the consequence? And that’s very helpful. Suppose you

15:42 wanted to understand the effects of all variations. Now, all variation there are a lot of variation because like you there are 3 billion base pairs and all of them can be changed three sort of times, right? If you A could be changed into a T or a C or a G, right? So, there are 9 billion possible single nucleotide variations that you can study. And for every single one of them, there’s a lot of data that you can sort of uh that you can extract as to what will be its effect at the

16:13 molecular level, at uh the effect on splicing, the effect on sort of gene expression, and and so forth. What Alpha Genome Atlas does, it basically pre-computes all of this. >> Ooh. >> It basically looks at what happened for all these variations and makes this massive data sets, a petabyte size uh sort of data set, and makes it available to the scientific community. >> That’s unbelievable. It feels like this AlphaFold moment where the inference of

16:43 time of folding became, you know, so quick that at some point Demis just said that, you know, let’s fold all the proteins. Like Atlas sounds like that for the genome. >> Exactly. So, I mean for for Alpha AlphaFold, we had um we made the predictions for uh structures of 250 million proteins, almost all the proteins that were known at that sort of time. But even the AlphaFold database, which has now been used uh by more than 4 a

17:15 users across 190 countries Alpha in terms of its actual size Alpha genome atlas is 30 times the size of Alpha fold database. >> Wow. >> So the scale at which Alpha genome can produce this the the detailed information about the effect of variation is unprecedented. >> All this from one mega base of DNA sequence. >> Yeah, so with with a one million sort of base pair window in in context.

17:46 >> For mutations that affect gene activity, there’s a fairly strong correlation between the predicted and the observed effect size. I saw in the paper that a row is about 0.5. >> Mhm. >> But but but that’s stunning. That’s that’s incredible. And my understanding is also that this doesn’t just predict whether a mutation matters, but often gets the magnitude of the effect roughly correct, too. Is that fair to say? >> Yes, absolutely. I think what we did

18:18 with especially Alpha genome atlas is we came up with a a new way to sort of help scientists sort of look at the data and explore this mass amount of data. So the Alpha genome variant impact score or the AVI score is sort of carefully sort of calibrated to say if the score is high, that means that there is that particular variant

18:49 is a variant that you should really think about and analyze sort of carefully. And if the AVI score is low, you can there’s high confidence that it will not have a dramatic impact on various different sort of phenotypes. >> Mhm. So to me this sounds like one of those root note problems where you you solve this problem and then it’s the applications can grow out of it in so many directions. I check AlphaFold

19:19 every now and then, which was one of these root node problems. And in the first couple years I could actually look through the papers that that used it and I tried to understand what they do. Now there’s so much that’s built on top of AlphaFold that it’s completely hopeless to for any of us to understand all of it. Does it look like AlphaGenome is going to be the same? >> Yeah, I think AlphaGenome with AlphaGenome we are trying to solve that root node problem of deciphering the genome, right? And and as you sort of mentioned, it it is

19:52 really truly a root node problem node problem in terms of its implications. So not only does it have implications for understanding sort of diseases better, it also has implications for how would you treat diseases? What are the sort of key things that you need to sort of understand about biology and what are the places where you can sort of control expression or what what variation sort of control expression of certain sort of protein which are relevant in that disease pathway. But

20:23 it’s not just applicable for understanding diseases and human health. It has implications that go beyond in in broader sort of biology. So in fact sort of now we are seeing a lot of interest in use of generative AI in synthetic biology. And again, when you’re sort of synthesizing sort of new organisms or new sort of proteins, like what are the properties that

20:55 we should be sort of thinking of, right? Like you would have seen DNA language models like Evo sort of come up and and people using them to sample different genomes to to solve different types of problems. And again, AlphaGenome gives you sort of a lens by which you can study the properties of those genomes. And so the implications of this model and its future sort of

21:26 variations, which we are working on, I think will be sort of in the same way very broad. >> I feel like I’ve been dropped into a science fiction movie. Like we we could only dream of of having technology like this when I was a child. It’s I think that’s unbelievable. How do we know that it learned mechanisms, not just correlations? Like usually that’s the that’s the problem with many of these papers. That the difficult part is actually proving the connection between the two. It’s almost impossible in many cases.

21:58 >> Yeah. So I think that’s a very good question. I think and that has been one of the sort of challenges, right? When you are looking in computational biology, that you don’t want just to learn all the statistical correlations. You want to have the model you want the model to be able to sort of understand the actual sort of causal sort of links that happen in that make the predictions possible. And if you think about it like in AlphaGenome, how that is sort of

22:30 encoded, one is that is in terms of the properties that it predicts. It predicts properties at the molecular sort of level. So it can you can really see when it makes a prediction about a particular variation about say splice sites or splicing or gene expression. So those are very sort of those are predictions which are which can be explained biophysically. Right? Rather than sort of correlationally that oh, this variation

23:01 happened basically causes that particular sort of disease. But, this Alpha genome is not saying that. It’s a basically actually telling you what is happening at the cellular sort of level. And then in terms of validating, uh what we have seen is actually when you make take these predictions and actually try to validate them in the lab, we see that those predictions make sense. And you can make novel uh sort of findings uh of uh of variation and and importance

23:31 of certain variants. >> Essentially, because the whole thing is based in physics, this is what essentially helps in terms of verification. >> Yeah, I think the tasks are more physically required to reason about the physics. Now, how the model is doing it, that’s something that we we are still sort of looking at and interpreting. But, uh the the the tasks that it is being asked to solve are grounded in physics. >> Now, you have this incredibly

24:02 sophisticated learning algorithm in AlphaFold genome. And then, in the paper on top of it, you have this tiny super simple layer of lasso regularization. And I found that really amusing. I imagine this almost like a a Formula 1 engine you invented, and it has a a little bicycle bell on top. >> Yeah, I I think the the this sort of shows the the power of the representation, right? What you want uh models like AlphaFold genome to exhibit

24:32 is sort of a a fundamental understanding of what they are what they are seeing or how they are perceiving uh the DNA sequence. So, in in some sense, most of the work should be done by the model in terms of the feature representation, and then the sort of the final sort of predictor on top should take a very simple sort of Yeah, almost trivial form because most of the work has happened at the representation sort of layer. >> What’s the next step? >> So, there are so many things that

25:05 we are working on, which is like with AlphaFold you know, the story does not end here. Like there is a lot that we need to do to improve AlphaFold you know, to make it even better in terms of its understanding of the genome. Um if you look at genomics and uh biology, biology sort of has a lot of different contexts. For example, different cells behave differently. Right? So, uh

25:35 making sort of AlphaFold you know, more uh sort of aware of the context in which it needs to make these predictions is one thing that we are sort of trying to work on. Um expanding the amount of data that AlphaFold you know, can be trained on so that it can sort of become much more accurate about different kinds of properties. Connecting these molecular phenotypes that AlphaFold you know, is able to sort of produce and showing and showing their connections and impact on

26:09 properties at the organism sort of at the human sort of level, right? The propensity to disease and so on. How do we sort of facilitate that work? All these things are a sort of directions that the team is now looking at. >> There’s so much going on. I don’t want to get greedy, but I just wanted to hear about the next steps. Like what what are you building on on top of this? That’s that’s awesome. You use Gemini with your son to explore science questions. Like how airplanes generate thrust.

26:39 >> [gasps] >> Has Gemini ever explained something to your son better than you could? So, where you said, “Oh man, that’s that’s way better than what I would have said.” >> Yeah, [laughter] so I I I it’s it’s not only the ability of these models in explaining concepts but by using different analogies and so on but also the ability of these models to actually show the theory in action.

27:10 So I was a few sort of weeks back I was trying to sort of explain to my son like what happens in a wind tunnel when sort of engineers are designing sort of say airplane sort of parts. And what are the effects and how do they do these simulations? And we asked Gemini to explain it and it it in fact it created a simulation.

27:41 And where sort of you could actually play around with different parameters and see what how the air flow sort of changes. Now it was not completely accurate but but it was a very good demonstration of what is possible right and like and creating these visual artifacts that help someone understand the concept. We are living in an incredible time because I I also remember when I first wrote my Navier-Stokes physics simulation for for

28:13 fluids. I remember when I first looked at the theory and I thought I’m never going to understand this. This is this is never happening and it took months and months of studying and and trying and now I I understand it very little about it but at least a basic simulator I can I can write. And you just here you just enter a prompt and you just got a simulation by the way on the side because the because the intelligence is so incredible that it it can do this

28:44 sort of thing like like just make up a wind tunnel test and and you can probably running real time you can see the streamlines as as it’s unbelievable and it’s only going to get better. Now I think we had about a 1 million X AI speed up in the last 10 years. If you factor in everything, it’s not just hardware. It’s if you factor in I don’t know transformers, how much better the implementations got the engineering the everything. Let’s say we got a 1 million X in the last 10

29:16 years. If in the next 10 years we have another 1 million X what could we do? >> There are so many open scientific challenges that are beyond our current capabilities. Simulating even a cell. Creating a virtual cell. Imagine the consequences of that, right? Like we would if you can completely sort of really understand the workings of a cell that will have amazing consequences for

29:46 the fight against diseases like cancer or synthetic biology and so forth. Now imagine not and that’s we are talking about a cell. Right? Imagine sort of simulating a organism. That will be sort of that is the power that can come from that understanding and that capability. But there’s so many things about the world that we still are scratching the surface on. Sort of understanding long-term climate for instance.

30:18 What are going to be the consequences of certain sort of actions on long-term sort of climate, sort of coming up with new material types that can help us sort of store energy, sort of transform energy in different forms in a much more efficient manner, understanding biology at from first principles to being able to truly design novel function for tackling uh some of the challenges that uh we are seeing both in human health as well as

30:50 sort of in agriculture and many other uh things that uh the world is facing. There are so many uh sort of um problems that can be unlocked with that progress. >> That was fantastic. Usually I ask these question people and I see that it kind of breaks their brain, too, because a 1 million x like 10 years ago, like 2016, we had no idea what what we could do today. And and it’s it’s it’s so exciting to think that okay, it’s if you add another 10 years, what would we be

31:21 capable of? And everyone is thinking so small, but but this one this one was really good. >> Nature is uh extremely sophisticated, right? Sort of we are and and really I think there’s a lot to look forward to in terms of um understanding the world. I I mean, understanding we’re talking about understanding cells. Uh understanding our own brain like uh is another sort of challenge. What is actually happening um in uh sort of materials? Why are they uh exhibiting

31:52 certain properties? We even sort of properties that we uh have seen uh forget about new types of properties, but properties that we have already seen like superconductivity. We don’t have a complete theory about superconductivity, right? We have one sort of narrow theory of superconductivity. Imagine the new properties that we are yet to sort of explore or uh sort of really uh crisply understand why these phenomenas happen and the ability to be able to design those objects. >> Fantastic. Pushmeet, every time we meet

32:25 I learn so much. And you know what the best part is? I I will go home and I cut these videos together myself. So, I’m going to watch it like five or six more times. And I guarantee you that every lesson there’s going to be something new that I learned. So, that was amazing. Thank you so much. >> Thank you. I use Lambda to reproduce AI research papers often in minutes. It’s also great to train your own models or fine-tune an existing one. Run inference or text-to-image or video easy peasy.

32:56 Running a deep seek chatbot or agent super fast, super reliable. Lambda gives you powerful Nvidia GPUs to run your own experiments. I test ideas from the papers I cover and moments [clears throat] later, results. Love it. Seriously, try it out now at lambda.ai/papers.