Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Flapping Airplanes co-founder Asher Spector explains why data efficiency is the greatest bottleneck to AI adoption: "To the extent that AI has been hard to integrate into the economy, I really think it's because models are much less data-efficient than humans. If you want it to learn a new...

92,663 görüntüleme • 9 ay önce •via X (Twitter)

13 Yorum

Eddie profil fotoğrafı
Eddie9 ay önce

@amspector100 so proud to defend principles that sound like buzzwords. data efficiency is a myth, and whole milk? really? sounds like corporate spin.

pique profil fotoğrafı
pique9 ay önce

@flappyairplanes @amspector100 Isn’t all about sensory integration? Give it some eyes and ears, let it taste things.. feel pain.. unless we mean dispose of the silicon frame, we have to release sensory ontology, and let it stumble around and talk to a person for a decade and see what happens.

Jose Danielle Inocentes profil fotoğrafı
Jose Danielle Inocentes9 ay önce

@amspector100 Great point data efficiency is often the real bottleneck, not just compute or model size. High-quality, well-labeled data matters more than volume. At LifeWood, we see how human in the loop workflows boost performance in low-data, high-stakes domains.

KingKuys2123 🎰🪳 profil fotoğrafı
KingKuys2123 🎰🪳9 ay önce

@amspector100 Data efficiency is indeed a critical challenge in AI adoption. Without a robust pipeline for sourcing and processing high-quality data, teams can quickly find themselves stalled. It’s essential to understand how to streamline these processes for better outcomes.

Nico profil fotoğrafı
Nico9 ay önce

@amspector100 The viral loop decoded: Simple mechanic + familiar reference + AI twist = shareability Flappy Bird nostalgia hit different when it's your own AI failing the same way you did in 2014. Emotional resonance scales better than technical complexity.

TESCREAL profil fotoğrafı
TESCREAL9 ay önce

@amspector100 This is literally the AGI problem.

Barua Piash profil fotoğrafı
Barua Piash9 ay önce

@amspector100 Learning to do more with less data is definitely the next big hurdle for the industry. We focus on this at Lifewood because efficient data exchange is what allows AI to work in specialized areas where you don't have millions of files to train on.

Joyanta Sarma profil fotoğrafı
Joyanta Sarma9 ay önce

@amspector100 How to make data efficient and how one gets to know data is efficient in the industry?

Meaning breaks before systems fail profil fotoğrafı
Meaning breaks before systems fail8 ay önce

@amspector100 Most “AI pilot purgatory” isn’t technical. It’s what happens after the output. Product, Risk, Compliance all interpret it differently, so no one agrees what to do next. You can’t scale AI if you can’t scale meaning.

Mumu Oyshi profil fotoğrafı
Mumu Oyshi9 ay önce

@amspector100 As AI evolves, improving data efficiency will be key to unlocking real world, scalable impact across industries. At Lifewood BG, we believe high quality, well managed data is the foundation for building smarter, more practical AI solutions.

zayn profil fotoğrafı
zayn9 ay önce

@flappyairplanes @amspector100 ok so how exactly do you make these models data efficient?

Fahim Nasim profil fotoğrafı
Fahim Nasim9 ay önce

@amspector100 That "fixed-wing" analogy really nails it. Just cranking things up with more brute force flapping tricks people into thinking we are making headway until suddenly we are stuck.

Tanjina Alam Riya profil fotoğrafı
Tanjina Alam Riya9 ay önce

@amspector100 I love how this keeps things so simple and real—at Lifewood Data Technology BG, we truly believe that the human element is what makes any tech actually worth using!

Benzer Videolar

Hunt: So, who’s right on data centers? President Trump or Governor Shapiro? Fetterman: Oh, the president is actually right overall. I mean, you know, uh, we we used to be moving forward on data centers and now, I mean, he's actually scared by the polls. So I mean, what really what's really motivated by more than just the polls overall, you know, I set out I set up my message on it on data centers just a couple days on X where I'm saying it's, you know, the president happens to be right in this. You know, I think it's it's very necessary that we win the war on AI. Uh, we, I think it's necessary because AI is going to transform our world. And, you know, it can be either us be the leaders or it can be the Chinese. And we could we could live under those rules and they're going to build unlimited data centers. And they're not really, uh, really stopped by with the kind of like democracy and the kinds of rules that, that we have overall, I think it's important. And I would remind people, like a lot of the opposition is, is been driven by the ccp and a lot of a lot of influence. So I think now withwith data centers, uh, also there's the facts now that it, it consumes a very, very, maybe one tenth of 1%, you know, compared to almonds and compared to other other things, part of our economy and also our land usage as well, too. Pennsylvania, you know, we are energy rich, we are water rich. And we have we're land rich now. So I think it's an important part of our economy, not just for Pennsylvania's but also the country right now.

Acyn

204,754 görüntüleme • 2 ay önce

Elon Musk On What It Takes To Build A Competitive AI Model Elon Musk breaks down the three factors that decide whether a foundation model can compete, and why the next frontier isn't human data at all. Speaking with Garry Tan, President and CEO of Y Combinator, Elon lays out what's actually required to build a large foundation model that's competitive: "You've got to get a lot of GPUs and have them train coherently and stably. Then it's like, what unique access to data do you have? I guess distribution matters to some degree as well like, how do people get exposed to your AI? Those are critical factors." But there's a problem with the data part of that equation. Echoing what a friend in the field has said, Elon explains that the industry has essentially run out of human-generated pre-training data: "You run out of tokens pretty fast, certainly of high-quality tokens. And then you need to essentially create synthetic data, and be able to accurately judge the synthetic data that you're creating, to verify: is this real synthetic data, or is it a hallucination that doesn't actually match reality?" That verification step is the hard part: "Achieving grounding in reality is tricky. But we are at the stage where there's more effort put into synthetic data. Right now we're training Grok 3.5, which is a heavy focus on reasoning." On reasoning, Garry Tan adds an interesting detail from researchers he's spoken to: hard science, particularly physics textbooks is very useful for training reasoning, whereas social science is "totally useless" for it. Elon's response: "Yes, that's probably true." He then points to where all of this is heading: "Something that's going to be very important in the future is combining deep AI in the data center or supercluster with robotics. So, things like the Optimus humanoid robot."

High Signal AI

21,751 görüntüleme • 4 ay önce