Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Waymo World Model

waymo.com

Post reply on HN
Print view View original

361–370 of 699 posts

Re: The Waymo World Model

#361

Post by smallmancontrov »

magicalist wrote: post #298
smallmancontrov wrote: post #228

Earlier quoted context omitted.

Tesla went nothing-but-nets (making fusion easy) and Chinese LIDAR became cheap around 2023, but monocular depth estimation was spectacularly good by 2021. By the time unit cost and integration effort came down, LIDAR had very little to offer a vision stack that no longer struggled to perceive the 3D world around it. Also, integration effort went down but it never disappeared. Meanwhile, opportunity cost skyrocketed…

> but monocular depth estimation was spectacularly good by 2021 It's still rather weak and true monocular depth estimation really wasn't spectacularly anything in 2021. It's fundamentally ill posed and any priors you use to get around that will come to bite you in the long tail of things some driver will encounter on the road. The way it got good is by using camera overlap in space and over time while in motion to fi…

It was spectacularly good before 2021, 2021 is just when I noticed that it had become spectacularly good. 7.5 billion miles later, this appears to have been the correct call.

Re: The Waymo World Model

#362

Post by schiffern »

mattlondon wrote: post #89

Suddenly all this focus on world models by Deep mind starts to make sense. I've never really thought of Waymo as a robot in the same way as e.g. a Boston Dynamics humanoid, but of course it is a robot of sorts. Google/Alphabet are so vertically integrated for AI when you think about it. Compare what they're doing - their own power generation , their own silicon, their own data centers, search Gmail YouTube Gemini wor…

  >I've never really thought of Waymo as a robot in the same way as e.g. a Boston Dynamics humanoid, but of course it is a robot of sorts.
So for the record, with this realization you're 3+ years behind Tesla.

https://www.youtube.com/watch?v=ODSJsviD_SU&t=3594s

Re: The Waymo World Model

#363

Post by smallmancontrov »

ChicagoDave wrote: post #316
hn_acc1 wrote: post #288

Earlier quoted context omitted.

Is that the official Tesla stat? I've heard of way more Tesla fatalities than that..

This is absolutely a Musk defender. FSD and Tesla related deaths are much higher. https://www.tesladeaths.com/index-amp.html

Autopilot is the shitty lane assist. FSD is the SOTA neural net.

Your link agrees with me:

> 2 fatalities involving the use of FSD

Re: The Waymo World Model

#364

Post by Fricken »

hn_acc1 wrote: post #288
smallmancontrov wrote: post #251

Earlier quoted context omitted.

Humans: 70 deaths in 7 billion miles FSD: 2 deaths in 7 billion miles Looks like FSD saves lives by a margin so fat it can probably survive most statistical games.

Is that the official Tesla stat? I've heard of way more Tesla fatalities than that..

I don't know what he's on about. Here's a better list:

https://en.wikipedia.org/wiki/List_of_Tesla_Autopilot_crashe...

Re: The Waymo World Model

#365

Post by caycep »

xnx wrote: post #295
kidk wrote: post #291

Earlier quoted context omitted.

Billions of subsidies? Im confused you talking about cars or trains.

No major US public transportation system is fully paid for by riders.

NYC congestion pricing seems to be working quite well though, and probably helps offset MTA costs.

Re: The Waymo World Model

#366

Post by caycep »

scoofy wrote: post #312
caycep wrote: post #265

All this work is impressive, but I'd rather have better trains

As someone who lives in the Bay Area we already have trains, and they're literally past the point of bankruptcy because they (1) don't actually charge enough maintain the variable cost of operations, (2) don't actually make people pay at all, and (3) don't actually enforce any quality of life concerns short of breaking up literal fights. All of this creates negative synergies that pushes a huge, mostly silent segment…

Maybe not BART but the new Caltrain electrification program seems to be a success and ridership and revenue are up

Re: The Waymo World Model

#367

Post by diamondage »

hibikir wrote: post #327
raphlinus wrote: post #272

Earlier quoted context omitted.

Not true at all. I interacted with Meena[1] while I was there, and the publication was almost three years before the release of ChatGPT. It was an unsettling experience, felt very science fiction. [1]: https://research.google/blog/towards-a-conversational-agent-...

The surprise was not that they existed: There were chatbots in Google way before ChatGPT. What surprised them was the demand, despite all the problems the chatbots have. The pig problem with LLMs was not that they could do nothing, but how to turn them into products that made good money. Even people in openAI were surprised about what happened. In many ways, turning tech into products that are useful, good, and don't…

The uptake forced the bigger companies to act. With image diffusion models too - no corporate lawyer would let a big company release a product that allowed the customer to create any image...but when stable diffusion et al started to grow like they did...there was a specific price of not acting...and it was high enough to change boardroom decisions

Re: The Waymo World Model

#368

Post by ses1984 »

yummypaint wrote: post #337

By leveraging Genie’s immense world knowledge, it can simulate exceedingly rare events—from a tornado to a casual encounter with an elephant—that are almost impossible to capture at scale in reality. The model’s architecture offers high controllability, allowing our engineers to modify simulations with simple language prompts, driving inputs, and scene layouts. Notably, the Waymo World Model generates high-fidelity,…

You could train it in simulation and then test it in reality.

Re: The Waymo World Model

#369

Post by Fricken »

smeeth wrote: post #95
mattlondon wrote: post #89

Suddenly all this focus on world models by Deep mind starts to make sense. I've never really thought of Waymo as a robot in the same way as e.g. a Boston Dynamics humanoid, but of course it is a robot of sorts. Google/Alphabet are so vertically integrated for AI when you think about it. Compare what they're doing - their own power generation , their own silicon, their own data centers, search Gmail YouTube Gemini wor…

I always understood this to be why Tesla started working on humanoid robots

It's so they can stick a Tesla logo on a bunch of chinese tech and call it innovation.
Post reply on HN