正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Why data is a trillion-dollar market "The bigger models scale, the more data you need. Data is a very durable need. If you believe in the scaling of models, then absolutely you should believe in the data market. I believe it's going to be at least a $100BN by... show more

Harry Stebbings

676,884 subscribers

21,443 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

Nam Đầu Tư 的头像

Nam Đầu Tư1 个月前

Data như giá vốn, phải không

Matthew Brown 的头像

Matthew Brown1 个月前

@HarryStebbings I am a non-tech small bus owner in south Alabama. Stumbled on this podcast a couple months ago and absolutely love the open, dynamic, thoughtful dialog. This episode was a great example. One of the best podcasts out there. Appreciate it.

Eitan Saban 的头像

Eitan Saban1 个月前

Compute scales fast. Clean, licensed, domain-specific data does not. The bottleneck was never the model... it was always what you fed it....

Sean O'Brien 的头像

Sean O'Brien1 个月前

The “more data solves everything” mindset is a religion, not a roadmap. If intelligence requires endless scraping of the internet, that’s a design flaw. HELIX proves the opposite: stability beats scale. You don’t need a trillion‑dollar data pile when the substrate is coherent.

Saurabh Shukla 的头像

Saurabh Shukla1 个月前

My experience in training image and video models is that we can scale down data requirement 10x if we curate data well and introduce algorithmic improvements.

Rabnoor Singh 的头像

Rabnoor Singh1 个月前

Lab spend alone caps out. Labs converge on the same corpora and pay less as curation improves. The non-substitutable data is operational exhaust only the enterprise owns, so the durable market is enterprise shaped.

Santiago Vega 的头像

Santiago Vega1 个月前

$1TRN feels like a stretch from aquí

aisafetycompute 的头像

aisafetycompute1 个月前

These predictions on data and/or compute are just a round about way of saying that scaling is going to continue to be the most critical way to improve models and not model architecture.

1024.com 的头像

1024.com1 个月前

The data market will be very prosperous.

相关视频

We believe the future of prediction markets is decentralised and permissionless. Anyone being able to make a market on anything. In order to do this you need AI and data you can verify and trust. This will all run on the Somnia blockchain.

We believe the future of prediction markets is decentralised and permissionless. Anyone being able to make a market on anything. In order to do this you need AI and data you can verify and trust. This will all run on the Somnia blockchain.

paul.somi

18,452 次观看 • 8 个月前

Sam Altman in a new interview says Orbital Data Centers are not going to matter at scale this decade: “I honestly think the idea, with the current landscape of putting data centers in space is ridiculous. If you do the very rough math of launch costs relative to the cost of power on earth and to say nothing how you are going to fix a broken GPU in space— they do break a lot unfortunately— we are not there yet. There will be a time, space is great for a lot of things, Orbital Data Centers are not something that is going to matter at scale this decade.” This clip isn’t going to age well for Sam.

Sam Altman in a new interview says Orbital Data Centers are not going to matter at scale this decade: “I honestly think the idea, with the current landscape of putting data centers in space is ridiculous. If you do the very rough math of launch costs relative to the cost of power on earth and to say nothing how you are going to fix a broken GPU in space— they do break a lot unfortunately— we are not there yet. There will be a time, space is great for a lot of things, Orbital Data Centers are not something that is going to matter at scale this decade.” This clip isn’t going to age well for Sam.

Nic Cruz Patane

72,344 次观看 • 7 个月前

"The enterprise's ability to leverage this depends on its ability to create training data as fast as it can. Not enough people are focused on training data. I need to get into the brains of the people who solve these problems, extract that knowledge, and codify it so I can write my own playbooks and rules. Every new phone call, every new case is a learning opportunity. You have to give the organisational knowledge to some learning system that you have to build." Nikesh Arora What does no one know that everyone should know about training data Brendan (can/do) Garrett Lord Jeff Richards Lin Qiao Yann LeCun Anastasios Nikolas Angelopoulos

"The enterprise's ability to leverage this depends on its ability to create training data as fast as it can. Not enough people are focused on training data. I need to get into the brains of the people who solve these problems, extract that knowledge, and codify it so I can write my own playbooks and rules. Every new phone call, every new case is a learning opportunity. You have to give the organisational knowledge to some learning system that you have to build." Nikesh Arora What does no one know that everyone should know about training data Brendan (can/do) Garrett Lord Jeff Richards Lin Qiao Yann LeCun Anastasios Nikolas Angelopoulos

Harry Stebbings

31,538 次观看 • 1 个月前

As Larry Ellison explains, there are two types of AI models: real-time models, also called AI on the edge, where you need ultra-low latency decisions (think autonomous driving or robotics), and models that don’t need an immediate response, like ChatGPT, where the system has time to reason. Real-time models require local compute inside the device, and these chips have nothing to do with the GPUs running in data centers. The AI-on-the-edge market is still largely untapped — and it’s going to be a multi-trillion-dollar opportunity. I believe $AMD will be one of the biggest beneficiaries

As Larry Ellison explains, there are two types of AI models: real-time models, also called AI on the edge, where you need ultra-low latency decisions (think autonomous driving or robotics), and models that don’t need an immediate response, like ChatGPT, where the system has time to reason. Real-time models require local compute inside the device, and these chips have nothing to do with the GPUs running in data centers. The AI-on-the-edge market is still largely untapped — and it’s going to be a multi-trillion-dollar opportunity. I believe $AMD will be one of the biggest beneficiaries

Daniel

151,698 次观看 • 9 个月前

Baseten's Charlie O'Neill on why the gap to the frontier is just compute and data: "Despite OpenAI and Anthropic and the closed source labs having more compute and more data, the recipe is the same. We're all scaling the same recipe here, and we're at slightly different points of the scaling curve. It's not like OpenAI or Anthropic have any secret sauce that differentiates them scaling up their multi-trillion parameter models from the rest of the open source ecosystem." "It really is just a matter of taking the core underlying architecture and training recipe, and throwing more compute and data at it, which is really promising." "Of course, these closed source labs probably have a long tail of optimizations they've made, which we're gonna continue to try and figure out in the open source community. But the core mechanism is there." "K3 is a great example of, well, if you do scale this recipe up, we're gonna get a pretty good model that's very, very close to the frontier, if not frontier itself." Charlie O'Neill Baseten

Baseten's Charlie O'Neill on why the gap to the frontier is just compute and data: "Despite OpenAI and Anthropic and the closed source labs having more compute and more data, the recipe is the same. We're all scaling the same recipe here, and we're at slightly different points of the scaling curve. It's not like OpenAI or Anthropic have any secret sauce that differentiates them scaling up their multi-trillion parameter models from the rest of the open source ecosystem." "It really is just a matter of taking the core underlying architecture and training recipe, and throwing more compute and data at it, which is really promising." "Of course, these closed source labs probably have a long tail of optimizations they've made, which we're gonna continue to try and figure out in the open source community. But the core mechanism is there." "K3 is a great example of, well, if you do scale this recipe up, we're gonna get a pretty good model that's very, very close to the frontier, if not frontier itself." Charlie O'Neill Baseten

MTS

17,404 次观看 • 1 个月前

Are humanoids the largest addressable market in history? Andrew Kang says "to understand that you have to look at what is the total market for human labor. It's something like 50% of GDP, some people put it at $40 trillion or $60 trillion." "The way that I would think about it is a humanoid can do everything that a human can do in the future, but it doesn't need to rest, it doesn't need to take breaks, it doesn't need to go on vacation. It's not going to quit on you, so you don't need to hire and retrain somebody else."

Are humanoids the largest addressable market in history? Andrew Kang says "to understand that you have to look at what is the total market for human labor. It's something like 50% of GDP, some people put it at $40 trillion or $60 trillion." "The way that I would think about it is a humanoid can do everything that a human can do in the future, but it doesn't need to rest, it doesn't need to take breaks, it doesn't need to go on vacation. It's not going to quit on you, so you don't need to hire and retrain somebody else."

Anthony Pompliano 🌪

109,720 次观看 • 3 个月前

It's easy for robots to nail a demo. It's much harder to get them to work reliably in the real world. The bottleneck is data. At Axis Robotics we're building a compounding data engine that combines simulation, ego-centric data and DAgger correction data at scale. Watch our CEO ChrisF(✱,✱) break down the data bottleneck, why messy data can still train good models, and what it takes to get robots out of the lab with blocmates. ⬇️

It's easy for robots to nail a demo. It's much harder to get them to work reliably in the real world. The bottleneck is data. At Axis Robotics we're building a compounding data engine that combines simulation, ego-centric data and DAgger correction data at scale. Watch our CEO ChrisF(✱,✱) break down the data bottleneck, why messy data can still train good models, and what it takes to get robots out of the lab with blocmates. ⬇️

Axis Robotics

23,713 次观看 • 1 个月前

Databricks' Ali Ghodsi on the clock that's forcing cyber and data into the same market: "It used to be like, okay, we have data and AI... you have a bunch of data and you run AI and machine learning, and that just lives separately." "And then you have the cyber world. Cyber world is, you know, we want to detect if bad people are trying to hack us." "But now on the data and AI side, we have agents running internally in the company. And the agents are also doing things with other people's agents, and they're producing a lot of data. Logs, trails, fingerprints that are being left." "All the data that's being produced needs to be analyzed. And the scale at which you need to do that is many, many orders of magnitude more than just one or two years ago." "2018, 2019, the time it would take from a CVE, a vulnerability being published, until you see it actually weaponized in the industry would be like two, three years." "That went down in 2022 significantly, but it was still like eight, nine months. So that's kind of fine, you have eight, nine months." "Now if you look at this curve from 2022 until now, it's down to basically hours, basically no time. Things get immediately weaponized." Ali Ghodsi

Databricks' Ali Ghodsi on the clock that's forcing cyber and data into the same market: "It used to be like, okay, we have data and AI... you have a bunch of data and you run AI and machine learning, and that just lives separately." "And then you have the cyber world. Cyber world is, you know, we want to detect if bad people are trying to hack us." "But now on the data and AI side, we have agents running internally in the company. And the agents are also doing things with other people's agents, and they're producing a lot of data. Logs, trails, fingerprints that are being left." "All the data that's being produced needs to be analyzed. And the scale at which you need to do that is many, many orders of magnitude more than just one or two years ago." "2018, 2019, the time it would take from a CVE, a vulnerability being published, until you see it actually weaponized in the industry would be like two, three years." "That went down in 2022 significantly, but it was still like eight, nine months. So that's kind of fine, you have eight, nine months." "Now if you look at this curve from 2022 until now, it's down to basically hours, basically no time. Things get immediately weaponized." Ali Ghodsi

a16z

38,473 次观看 • 4 天前

$MU is going to $2000 and therefore be a 2 trillion market capitalization! You have to believe in yourself. You have to have self confidence, faith, and do the work. Sell 10 $MU at $2,000 and put the computer in your closet.

$MU is going to $2000 and therefore be a 2 trillion market capitalization! You have to believe in yourself. You have to have self confidence, faith, and do the work. Sell 10 $MU at $2,000 and put the computer in your closet.

Chris and the Markets

45,417 次观看 • 3 个月前

Mark Cuban: OpenAI is shitting away their money. They'll never get a return on that trillion dollar spend. "There's a lot of FUD being put out about the spending. We're going to spend a trillion dollars because we need all this data center capacity. Well, the data center, the ability to process is going to get faster, cheaper" "I think a lot of the numbers that they're throwing out there aren't going to come to fruition, which is why I say they're full of shit" "We don't know if the business of foundational models is going to be like the streaming industry where there's one leader and a bunch of players that make money, or some that make money at least, or search where there's effectively one company" "So they need to raise all the money, go all in and spend everything they can, kiss all the rings around the world in hopes of being the one" "It's going to be very difficult, but I don't think it's going to pay off the way they expect" "They're pissing away the money at scale. It's hard to do, right? But if you don't go all in like that, you can't keep on raising money."

Mark Cuban: OpenAI is shitting away their money. They'll never get a return on that trillion dollar spend. "There's a lot of FUD being put out about the spending. We're going to spend a trillion dollars because we need all this data center capacity. Well, the data center, the ability to process is going to get faster, cheaper" "I think a lot of the numbers that they're throwing out there aren't going to come to fruition, which is why I say they're full of shit" "We don't know if the business of foundational models is going to be like the streaming industry where there's one leader and a bunch of players that make money, or some that make money at least, or search where there's effectively one company" "So they need to raise all the money, go all in and spend everything they can, kiss all the rings around the world in hopes of being the one" "It's going to be very difficult, but I don't think it's going to pay off the way they expect" "They're pissing away the money at scale. It's hard to do, right? But if you don't go all in like that, you can't keep on raising money."

Brad

92,187 次观看 • 2 个月前

Kaitlan Collins: “Do you think undocumented immigrants should have access to federally funded healthcare?” Rep. Alexandria Ocasio-Cortez (D-NY): “I believe personally that healthcare is a human right. I believe that every person should be able to go to the doctor.” Kaitlan Collins: “But if you could choose, do you believe [the law should be changed, allowing illegal aliens to have free healthcare]?” Rep. Alexandria Ocasio-Cortez (D-NY): “Pardon?… I believe in a single-payer healthcare system. Where if you go in and need a doctor, you can get the medical attention you need.”

Kaitlan Collins: “Do you think undocumented immigrants should have access to federally funded healthcare?” Rep. Alexandria Ocasio-Cortez (D-NY): “I believe personally that healthcare is a human right. I believe that every person should be able to go to the doctor.” Kaitlan Collins: “But if you could choose, do you believe [the law should be changed, allowing illegal aliens to have free healthcare]?” Rep. Alexandria Ocasio-Cortez (D-NY): “Pardon?… I believe in a single-payer healthcare system. Where if you go in and need a doctor, you can get the medical attention you need.”

RedWave Press

3,503,663 次观看 • 11 个月前

Palantir CEO Alex Karp on why Europe has no tech scene: "You basically have different parts of the stack: you have the GPU part—chips." "In an enterprise, you're going to have a data integration part of the stack. You can do that by hand." "If you want civil liberties—we do that." "You have an application part of the stack—ontology." "And you have the LLMs, both closed and open models." "To have a tech scene in Europe, you need world-leading components in all those parts. That's not realistic." "So you're going to have to figure out which components are actually the ones that could advance European industry, European sovereignty." "What's really happening in Europe is, you have bureaucrats whose primary idea is, 'How do I protect the market against American companies?'" "Everything else is downstream." Via Mathias Döpfner

Palantir CEO Alex Karp on why Europe has no tech scene: "You basically have different parts of the stack: you have the GPU part—chips." "In an enterprise, you're going to have a data integration part of the stack. You can do that by hand." "If you want civil liberties—we do that." "You have an application part of the stack—ontology." "And you have the LLMs, both closed and open models." "To have a tech scene in Europe, you need world-leading components in all those parts. That's not realistic." "So you're going to have to figure out which components are actually the ones that could advance European industry, European sovereignty." "What's really happening in Europe is, you have bureaucrats whose primary idea is, 'How do I protect the market against American companies?'" "Everything else is downstream." Via Mathias Döpfner

Jawwwn

65,161 次观看 • 2 个月前

"If you're an analytical SaaS company, it's over. It's over." - Palo Alto Networks CEO Nikesh Arora "What is an analytical SaaS company? It is a company that says, “I'm going to collect a lot of data for you and analyze it for you.” I don't need you to analyze it for me. I can run models against the data and analyze it myself. Think about it: almost every SaaS company has a marketplace. You can buy applications from the Salesforce Marketplace. What do those applications say? “You have Salesforce data. I'm a marketplace app. Use me, and I'll help you analyze that data.” But I don't need to do that. You don't need those applications anymore. I can simply run an LLM against the data. Therefore, all the additional functionality that has traditionally been sold to us as incremental software modules may no longer need to be sold separately. I would much rather have an LLM run against the data." ---- From "All-In Podcast" YouTube channel, (full video link in comment)

"If you're an analytical SaaS company, it's over. It's over." - Palo Alto Networks CEO Nikesh Arora "What is an analytical SaaS company? It is a company that says, “I'm going to collect a lot of data for you and analyze it for you.” I don't need you to analyze it for me. I can run models against the data and analyze it myself. Think about it: almost every SaaS company has a marketplace. You can buy applications from the Salesforce Marketplace. What do those applications say? “You have Salesforce data. I'm a marketplace app. Use me, and I'll help you analyze that data.” But I don't need to do that. You don't need those applications anymore. I can simply run an LLM against the data. Therefore, all the additional functionality that has traditionally been sold to us as incremental software modules may no longer need to be sold separately. I would much rather have an LLM run against the data." ---- From "All-In Podcast" YouTube channel, (full video link in comment)

Rohan Paul

52,065 次观看 • 8 天前

Kevin Hassett: "The data can't be propaganda. The data has to be something you can trust, because decision-makers throughout the economy trust that these are the data that they can build a factory because they believe, or cut interest rates because they believe. And if the data aren't that good, then it's a real problem for the US."

Kevin Hassett: "The data can't be propaganda. The data has to be something you can trust, because decision-makers throughout the economy trust that these are the data that they can build a factory because they believe, or cut interest rates because they believe. And if the data aren't that good, then it's a real problem for the US."

Aaron Rupar

599,432 次观看 • 1 年前

LLMs had the internet. Robotics doesn’t, which is why we’re bringing the Scale AI data engine into the physical world. Robotics won’t be solved by blindly collecting 100x more demos. Raw trajectories need structure (intent, subgoals, failures, recoveries, edge cases, quality signals) or you just average mistakes. At Scale Labs, we’re building that data flywheel, mapping the right data to the right capabilities and scaling what works globally !

LLMs had the internet. Robotics doesn’t, which is why we’re bringing the Scale AI data engine into the physical world. Robotics won’t be solved by blindly collecting 100x more demos. Raw trajectories need structure (intent, subgoals, failures, recoveries, edge cases, quality signals) or you just average mistakes. At Scale Labs, we’re building that data flywheel, mapping the right data to the right capabilities and scaling what works globally !

jade

15,262 次观看 • 4 个月前

#WATCH | Delhi: On the #CasteCensus, author and Advaita teacher Acharya Prashant says, "Any action depends on the intention. Caste census means collecting more data, authentic data and data in itself are neither forward nor backwards, good nor bad. It depends on what you want to what you intend to do with the data. If you want to identify the marginalised groups in a better way, so that more accurate and more efficient policy making can happen, then it's a good step, a forward step... On the other hand, if you use this data to cement cost identification further, then obviously it's a step backwards. If you use this data for electoral gains by targeting particular caste groups concentrated in particular electorates or geographies, then obviously it's a backwards thing..."

#WATCH | Delhi: On the #CasteCensus, author and Advaita teacher Acharya Prashant says, "Any action depends on the intention. Caste census means collecting more data, authentic data and data in itself are neither forward nor backwards, good nor bad. It depends on what you want to what you intend to do with the data. If you want to identify the marginalised groups in a better way, so that more accurate and more efficient policy making can happen, then it's a good step, a forward step... On the other hand, if you use this data to cement cost identification further, then obviously it's a step backwards. If you use this data for electoral gains by targeting particular caste groups concentrated in particular electorates or geographies, then obviously it's a backwards thing..."

ANI

82,457 次观看 • 1 年前

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?

Pat Grady

66,577 次观看 • 1 个月前

Dario Amodei reveals the two convictions that made him leave OpenAI to start Anthropic "The first conviction was the scaling laws" "If you scale up models, give them more data and more compute, you find incredible increases in performance. I was finding that in 2019 with GPT-2" "There were a lot of folks inside and outside who didn't believe it at all. We made the case to leadership, this is going to be a big deal" "The second was, if these models are going to match the capability of the human brain, we better get this right" "Despite a lot of language about doing it in the right way, I was just not convinced there was a real and serious conviction to do it the right way"

Dario Amodei reveals the two convictions that made him leave OpenAI to start Anthropic "The first conviction was the scaling laws" "If you scale up models, give them more data and more compute, you find incredible increases in performance. I was finding that in 2019 with GPT-2" "There were a lot of folks inside and outside who didn't believe it at all. We made the case to leadership, this is going to be a big deal" "The second was, if these models are going to match the capability of the human brain, we better get this right" "Despite a lot of language about doing it in the right way, I was just not convinced there was a real and serious conviction to do it the right way"

Jaynit Makwana

248,140 次观看 • 4 个月前