will depue
@willdepue • 65,929 subscribers
dei ex machina ex-@openai (sora 1 & 2, posttraining o3/4o, pretraining moonshots)
Shorts
Videos
you tend to hear this a lot from people outside or new to ML, and I often point to a talk Ilya gave a few years back: 1) think of any decent deep neural net that has enough memory and sequential ops as just a big parallel computer 2) training this neural net is doing search over computer programs that maximize your objective 3)unless you have some large bottleneck (and given you can successfully optimize this system) you’ll find that these parallel computers are highly robust to architectural changes. 4) this is because computers are great at simulating each other. your new architecture can usually be straightforwardly simulated ‘inside’ your old architecture. 5) it’s not that architecture doesn’t matter, but it mostly matters with respect to (1) fundamental bottlenecks in this parallel computer (2) modifications that make models easier to optimize, since this argument only holds if your optimization is good (3) compute efficiency/system efficiency wins that make learning easier or faster. 6) it’s quite possible that new architectures will lead to breakthroughs in machine learning, but we should first start with bottlenecks, not naturalist intuitions about the ‘form’ of AI should take. until you understand this it seems surprising that small models trained longer are better than undertrained big models, that depth and width are surprisingly interchangeable, that talking to a model with an MoE or sparse attention or linear attention is approximately the same iso evals.
will depue214,428 görüntüleme • 5 ay önce
FIGMA-OS: The first Turing-complete Figma file. SPECS: 8-bit architecture, 512 bits of RAM, 16 bytes of Program Memory, MISC instruction set of 16 OPCODES, 10HZ clock speed, 4 fast access registers, binary-tree RAM/ROM memory. MOTIVATIONS: For the meme. HOW: Explained below.
will depue338,114 görüntüleme • 2 yıl önce
sora is launching today to all chatgpt pro and plus users! it's been a big effort to make this possible + i think the product is really fun & intuitive. my fav thing to do is generate fake historical found footage. video inpainting is also really strong. have fun!
will depue134,004 görüntüleme • 1 yıl önce
you me, us, the oakland hills, the rivian r1t, and the dream of homeownership
will depue11,768 görüntüleme • 3 ay önce
i’m scrolling on short form content you couldn’t even imagine
will depue27,732 görüntüleme • 1 yıl önce
retro is the best app i’ve used this year. highly recommend trying it out. happy 2026!
will depue13,855 görüntüleme • 5 ay önce
Daha fazla içerik yok.