The fact that Edison is pervasively over-credited is really another example of the highly visible executive claiming personal credit for the labors of employees.
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, multi-sensor outputs that include both camera and lidar data.
How do you know the generated outputs are correct? Especially for unusual circumstances?
Say the scenario is a patch of road is densely covered with 5 mm ball bearings. I'm sure the model will happily spit out numbers, but are they reasonable? How do we know they are reasonable? Even if the prediction is ok, how do we fundamentally know that the prediction for 4 mm ball bearings won't be completely wrong?
There seems to be a lot of critical information missing.
The idea is that, over time, the quality and accuracy of world-model outputs will improve. That, in turn, lets autonomous driving systems train on a large amount of “realistic enough” synthetic data.
For example, we know from experience that Waymo is currently good enough to drive in San Francisco. We don’t yet trust it in more complex environments like dense European cities or Southeast Asian “hell roads.” Running the stack against world models can give a big head start in understanding what works, and which situations are harder, without putting any humans in harm’s way.
We don’t need perfect accuracy from the world model to get real value. And, as usual, the more we use and validate these models, the more we can improve them; creating a virtuous cycle.
I don't think you say "ok now the car is ball bearing proof."
Think of it more like unit tests. "In this synthetic scenario does the car stop as expected, does it continue as expected." You might hit some false negatives but there isn't a downside to that.
If it turns out your model has a blind spot for albino cows in a snow storm eating marshmallows, you might be able to catch that synthetically and spend some extra effort to prevent it.
The blackouts circumstance was because they escalate blinking/out of service traffic lights to a human confirmed decision, and they experienced a bottleneck spike in those requests for how little they were staffed. The Waymo itself was fine and was prepared to make the correct decision, it just needed a human in the loop.
In the video from the parade... there's just... people in the road. Like, a lot of small children and actual people on this tiny, super narrow bridge. I think that erring on the side of "don't think you can make it but accidentally drag a small child instead" is probably the right call, though admittedly, these cases are a bit wonky.
>The blackouts circumstance was because they escalate blinking/out of service traffic lights to a human confirmed decision
Which isn't really a scalable solution. In my city the majority of streetlights switch to blinking yellow at night, with priority/yield signs instead. I can't imagine a human having to approve 10 of these on any route.
From their blog post they give the sense that they had the human review "just to be safe", but didn't anticipate this scenario. They've probably adjusted that manual review rule and will let the cars do what they would've done anyway without waiting for manual review/approval.
Isn't that true for any scenario previously unencountered, whether it is a digital simulation or a human? We can't optimize for the best possible outcome in reality (since we can't predict the future), but we can optimize for making the best decisions given our knowledge of the world (even if it is imperfect).
In other words it is a gradient from "my current prediction" to "best prediction given my imperfect knowledge" to "best prediction with perfect knowledge", and you can improve the outcome by shrinking the gap between 1&2 or shrinking the gap between 2&3 (or both)
seems like the obvious answer to that is you cover a patch of road with 5mm ball bearings, and send a waymo to drive across it. if the ball bearings behave the way the simulation says they would, and the car behaves the way the simulation said it would, then you've validated your simulation.
do that for enough different scenarios, and if the model is consistently accurate across every scenario you validate, then you can start believing that it will also be accurate for the scenarios you haven't (and can't) validate.
>> How do you know the generated outputs are correct? Especially for unusual circumstances?
You know the outputs are correct because the models have many billions of parameters and were trained on many years of video on many hectares of server farms. Of course they'll generate correct outputs!
I mean that's literally the justification. There aren't even any benchmarks that you can beat with video generation, not even any bollocks ones like for LLMs.
I think because here there's no single correct answer that the model is allowed to be fuzzier. You still mix in real training data and maybe more physics based simulation of course but it does seem acceptable that you synthesize extremely tail evaluations since there isn't really a "better" way by definition and you can evaluate the end driving behavior after training.
You can also probably still use it for some kinds of evaluation as well since you can detect if two point clouds intersect presumably.
In much a similar way that LLMs are not perfect at translation but are widely used anyway for NMT.
It's not too late for a political solution. If Congress stopped abdicating it's constitutional duty all these problems could be solved quickly. If you're in the US, visit your representatives offices IN PERSON, calling is a distant second best.
In a hilarious turn of events the senate has passed a funding bill with the DHS bill separated out since this comment.
I don’t know if this means zero DHS funding until the piecemeal bill passes or something less dramatic but I fully expect they will break all previous records for funding DHS shortly after.
US senators request for visit forms are just for show if you're not "important". That said maybe just requesting an in person visit is enough. I would definitely not recommend just showing up at a US senator's public office building (and you probably didn't mean this, just making it clear for everyone).
The political solution is 30 year term limits for Senate and House (5 terms and 15 terms respectively). The current system lack of term limits incentivizes inaction
Term limits for elective office are fake, nonworking solution to problems caused by a broken electoral system; the solution is to fix the electoral system, not to impose term limits (which solve nothing.)
Term limits make the problem worse; the main fix is to abandon strict single-member-district first-past-the-post for a more proportional system for legislative elections (for Presidential elections the problem is harder, both because there is no good, easy fix for an inherently single-winner election and because almost any meaningful change will require a Constitutional amendment which is quite difficult even if you can nail down what to do.)
For the House, using a multimember ranked ballots system like Single Transferrable Vote in districts capped at a size of 5 members in states with more than one rep would work tolerably well (especially if combined with increasing the total number of seats beyond the currently-legislated fixed 435.) This does all of support more parties, reduce or eliminate [depending on the exact method chosen] spoiler effects for voting first choice for parties that don't win seats reducing the need for tactical voting, reduce incumbent protection without removing voter choice [because parties are encouraged to run more candidates than they are likely to win], and produce a body that better represents the preferences of the electorate.
The Senate is more complicated because of the 1/3 per class rule, but it can be made slightly better (in order from smallest to largest changes), by:
1. Adopting a single-winner ranked choice method instead of first-past-the-post for Senate elections.
2. Increasing the size of the Senate to three seats per state (electing one Senator from each stare in each of the three two-year classes), combined with #1.
3. Increase the size of the Senate to six (2/state/class) or nine (3/state/class), using a ranked ballots multiwinner proportional system like STV for elections. (3/state/class keeps the majority a significant threshold.
Because of the Constitutional manner of apportioning electors, increasing the size of the House makes Presidential election voting power more equal by population while increasing the size of the Senate makes it less; for this reason, if doing the fixes for Congress discussed above, I would favor not increasing the size of the Senate by a greater multiple than thet of the house, so three per state in the Senate would go with at least a 50% increase in the size of the House, 2/state/class would go with at least tripling the House, 3/class/state would go with at least a 4.5× on the size of the House.
All are very-sound ideas. Regrettably, they'd be tough to explain to the voters — and the vested interests would oppose fiercely.
A good start might be to just triple the size of the House to approximately match the Repr.-to-population ratio when the present 435 number was legislated.
These people aren't temporarily insane, they have always been this way. The same hatred and stupidity have been prevalent in US dinnertable discussions for decades, but much less in the actual halls of power because we used to have more collective sense to not grant people like that authority over others in general. If the rest of American society regains its agency, the toxic %25 will just go back to corroding the country as they were before. They are secure in knowing they will not be treated in the way they would treat others if given the opportunity.
I found it odd they specifically said not to make a git repo for the page, GitHub is one of the easiest ways I know to publish a website. It just can't be commercial etc
A key property of QCD is that unlike electrodynamics, the forces between interacting objects increase with distance (quark confinement). This is what breaks the usual style of expansions used to simplify problems. It's hard to overstate how important this is.
One of the implications is that there are many interactions where most possible Feynman diagrams contribute non-negligibly. The advances in theory arguably have much more to do with improvements in techniques and the applied math used, such as in lattice QCD and Dean Lee's group for instance.
If it's the computer of an older family member or something, just put Firefox and ubo on their system for them and be done with it. They will use whatever software is preloaded, and being shown how to use it is a much lower barrier to entry than the cognitive load of finding, vetting, installing, and configuring new software.
I used to try to patiently explain why people should do xyz. Now I explain to people why I'm going to change xyz on their device, and if they don't slam the breaks I just do what needs to be done right then. If someone doesn't know what an adblocker is they are getting one so they can see for themselves and reflect on what companies have been putting them through for years to make some incremental amount of money.
Part of the problem is that software engineers aren't real engineers. Engineering disciplines formally recognize their responsibilities to the public, and are expected to refuse to build dangerous or harmful systems.
The mechanical engineers who design cars and the civil engineers who design the roads and bridges they traverse are held to these standards, and hold themselves to these standards. The software engineers who write code that actually controls vehicles in practice have no such culture. Relevant professional organizations like the ACM should be leading the charge, but they aren't because their membership doesn't care.
One solution is to license software engineers. What do people working in the industry think about that?
False comparison... There are also mechanical engineers that design trashy gewgaws. And electronic engineers designing giftcard chips.
And creating regulations for the word "engineer" is just a bad idea. Instead the common solution is independent certification bodies (perhaps with some government clout for practices that endanger people).
And regardless, you can only regulate individuals within your jurisdiction. Global commerce and services makes the idea of controlling the word engineer fruitless.
I suppose my point was that it’s detached from reality to say that real engineers refuse to build “dangerous” systems.
All of the most dangerous systems are built by engineers and outside the most progressive circles it’s quite obvious that these systems must exist amidst the anarchy of geopolitics.
It might be more convenient to purchase pre-blended mixes for many applications. For example 90% argon 10% isobutane. In welding this would be "impure" but for ionization counting it's exactly what you want.
Interactions between species are scarcely understood in general, if they are known at all. It's only very recently that the existence of mycelial networks was discovered. It's only very recently that the importance of micro biome and it's role in health is starting to be recognized. It's only in hindsight that impact of the near extinction of vultures in India on human health was understood.
History has shown industrialized humans to be dangerously ignorant of environmental systems, and almost every action we take with regard to these systems is destructive. Every extinction is irreversible. Things are so wildly out of equilibrium now that it's no longer possible to return to the equilibria from our past.
Ecological collapse isnt some mild inconvenience that makes milk more expensive. Once it has happened, ecological collapse cannot and will not be undone by the seriousness of "business." This type of thinking embodies exactly the kind of arrogant hubris that led us into this situation. The negative feedback loops that have kept earth habitable for us so far aren't laws of nature, and no-one knows how far they can be bent before breaking, or how they even work.
reply