Google says AI weather model masters 15-day forecast • Hacker News Board

Re: Google says AI weather model masters 15-day forecast

#151

Post by urbandw311er » Wed, Dec 11, 2024, 8:39 AM UTC

crowcroft wrote: post #49

Always42 wrote: post #15

Based on the Gemini release it’s hard to take what Google claims at face value.

Aside from the fact you're conflating two very different things comparing this to Gemini, what exactly is the problem with the Gemini? Specifically just that the release was a bit awkward and had some problems? I've found the latest model releases to be very good compared to other frontier models.

Probably a reference to when Google was widely perceived to rush out the first Gemini release, neglecting to mention it did lots of weird racist stuff.

Re: Google says AI weather model masters 15-day forecast

#152

Post by urbandw311er » Wed, Dec 11, 2024, 8:42 AM UTC

As long as the AI in charge of weather forecasting never ever comes within the control of the AI charged with fixing climate change.

GOAL: Fix world’s problems. OBSERVED CAUSE: Too many humans. DECISION: Tell humans about impending hurricane? Yes/No

Re: Google says AI weather model masters 15-day forecast

#153

Post by ClassyJacket » Wed, Dec 11, 2024, 8:47 AM UTC

urbandw311er wrote: post #152

As long as the AI in charge of weather forecasting never ever comes within the control of the AI charged with fixing climate change. GOAL: Fix world’s problems. OBSERVED CAUSE: Too many humans. DECISION: Tell humans about impending hurricane? Yes/No

I think it'll reach the conclusion it should kill us all regardless

Re: Google says AI weather model masters 15-day forecast

#154

Post by nojs » Wed, Dec 11, 2024, 8:47 AM UTC

Terr_ wrote: post #146

Ankaios wrote: post #128

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…

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

Re: Google says AI weather model masters 15-day forecast

#155

Post by ovj129 » Wed, Dec 11, 2024, 8:53 AM UTC

This a great use case for AI to be used

Re: Google says AI weather model masters 15-day forecast

#156

Post by az226 » Wed, Dec 11, 2024, 9:09 AM UTC

YeGoblynQueenne wrote: post #79

The catch: the model is predicting the past: >> But DeepMind said GenCast surpassed the precision of the center's forecasts in more than 97 percent of the 1,320 real-world scenarios from 2019 which they were both tested on.

Yes, but it was trained on 2018 data and earlier.

Re: Google says AI weather model masters 15-day forecast

#157

Post by drexlspivey » Wed, Dec 11, 2024, 9:26 AM UTC

genewitch wrote: post #133

Ankaios wrote: post #128

Turns out the Google AI's 15-day forecasts are for the weather in Mountain View. Which I can forecast 15 days out, too.

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!'"

Thanks Ollie

Re: Google says AI weather model masters 15-day forecast

#158

Post by Dylan16807 » Wed, Dec 11, 2024, 10:03 AM UTC

toxik wrote: post #150

Dylan16807 wrote: post #98

Earlier quoted context omitted.

> obviously It's not obvious to me. Care to elaborate? The only one that strikes me as "obviously" different is the Nobel prize that isn't really a Nobel prize, the one for economics.

The peace prize isn’t awarded by the Nobel committee either.

How so?

The Nobel committee picks candidates for all the prizes, and the final decisions are split up over four different institutions.

The only argument I could see along these lines would be favoring the Royal Swedish Academy of Sciences in particular, but that would mean that chemistry, physics, and economics count but medicine doesn't count. And that's just confusing.

Re: Google says AI weather model masters 15-day forecast

#159

Post by benhurmarcel » Wed, Dec 11, 2024, 10:25 AM UTC

Terr_ wrote: post #146

Ankaios wrote: post #128

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…

https://xkcd.com/937/

Re: Google says AI weather model masters 15-day forecast

#160

Post by beernet » Wed, Dec 11, 2024, 10:41 AM UTC

BadHumans wrote: post #56

I'm friends with a meteorologist and the 15+ day forecast is the bane of their existence because you can't accurately forecast beyond a week so I would love to know how they are measuring accuracy. The article doesn't say and I know the paper is going to go over my head.

> you can't accurately forecast beyond a week

Totally wrong. You cannot generalize such a statement because it depends on the micro and macro weather conditions. A very stable situation makes it very easy to forecast one week and beyond. On the other hand, there can be situations where you cannot accurately predict the next 12 hours (e.g. cold air pool).