Hacker News Reader

Comment by Ankaios | Hacker News Reader

Turns out the Google AI's 15-day forecasts are for the weather in Mountain View.

Which I can forecast 15 days out, too.

There's a little cautionary story I like to tell about predictions and probabilities

There is a man living near a volcano. He has put up a sign outside his house for travelers, proudly declaring: "Will not erupt today. Accuracy: 100%."

One night, after thirty years of this, the volcano erupts for a few hours at night, oozing magma on its opposite side.

The next morning, the man is grateful that his house is fine, but feels a pang of sadness as he replaces the famous sign with a new one: "Will not erupt today. Accuracy rate: 99.99%."

Alternatively if he predicted the probability of eruption every day as 0.01%, he’d be a perfect forecaster!

https://xkcd.com/937/

https://hasthelargehadroncolliderdestroyedtheworldyet.com/

https://www.youtube.com/watch?v=CUF3Of0S3tE&t=37s

Yes, most people can predict weather in the dessert. But why do you claim this is what happened here? Or was it a joke? Because people took it serious.

Neither the article, nor the linked paper state that. But they have all the details on precision and condition.

https://www.nature.com/articles/s41586-024-08252-9

It was a joke about how silly valley based companies will claim the moon and back and then design a car that doesn’t know dumping snow in the boot is bad.

The work was done by DeepMind, which is in the UK. Weather in the UK is quite variable and difficult to predict (which is why the English are always talking about it).

English weather depends on wind direction:

  south-west: mild, wet
  north-west: cool, wet
  north-east: cold, dry
  south-east: hot, dry

If you also use a simple barometer, to get pressure level (say, 4 bands) and pressure change direction (rising/falling), you can be 95% accurate.

Final finesse:

  Red sky at night shepherd's delight
  Red sky in the morning shepherd's warning

Here's the paper: https://www.nature.com/articles/s41586-024-08252-9

It was trained on global data, and makes global forecasts.

Wait, we're actually reading the article now instead of making jokes?

Unfortunately I think a lot of people seem to have taken Ankaios' joke as an actual claim about the research.

(ex: https://news.ycombinator.com/item?id=42388734 https://news.ycombinator.com/item?id=42387291 https://news.ycombinator.com/item?id=42385397)

Lemme guess:

Night and morning low clouds, burning off in the afternoon.

Source: lived in Los Angeles for a dozen years, saw the weather forecast a few times

Nope. An excerpt from https://www.nature.com/articles/s41586-024-08252-9:

>Figure 2 shows some of the forecast samples of GenCast for Typhoon Hagibis, shortly before it made landfall in Japan on 12 October 2019. Figure 2b–e,g,h–k,m shows that GenCast forecasts are sharp and have spherical harmonic power spectra that closely match the ERA5 ground truth at both 1- and 15-day lead times

Seriously. Let's see an accurate forecast for Cleveland, Ohio. Even local forecasters can barely get the next day correct on any sort of consistent basis.

And Apple Maps at launch worked great... in Cupertino.

I can beat you. I can forecast it for 16 days.

haha, one of the few times my gut reaction to something on HN was dead on.

"The easiest job in the world is the weatherperson in San Diego... And now, Ryan, what's the weather going to be like today?'

'uh, nice. back to you!'"

San Diego weather forecasting is the meteorological equivalent of being on cruise control

> 80% of the time, the WeatherMan is right every time!

Thanks Ollie

Reply on news.ycombinator.com