Hacker ApprovedDepartments

WeatherNext

Weather forecasting model in AI tools

People recommend it for forecast accuracy, especially for hurricane tracks, and for practical uses like shipping and disaster preparation. The most common caveat is that its outputs and methods lack detail and are hard to read.

People recommend it for forecast accuracy, especially for hurricane tracks, and for practical uses like shipping and disaster preparation. The most common caveat is that its outputs and methods lack detail and are hard to read.

24 people gave an opinion

recommend it
15
criticize it
9
approval share
63%
Each figure is one person. RecommendsCriticizes

Recommended in 4 of 13 months

  1. November 2025: recommended
  2. December 2025: recommended
  3. January 2026: not recommended
  4. February 2026: not recommended
  5. March 2026: not recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: not recommended
  9. July 2026: not recommended
  10. August 2026: recommended
  11. September 2026: recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 15 people recommend itNeeds 10 or more, met.
  • 1.6 recommenders for every criticNeeds 2 to 1 or better, not met.
  • Recommended in 4 of 13 monthsNeeds 4 or more, met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Accurate forecasts, especially hurricane tracks

    “the new hurricane model was breathtakingly good this season when tested against actual hurricane paths”

    Comment from 17 Nov 2025 in “WeatherNext 2: Our most advanced weather forecasting model”

    “At one point they did release the most accurate weather model by far”

    Comment from 8 Sep 2026 in “WeatherNext 3”

    “The accuracy of WeatherNext 2 is astounding.”

    Comment from 20 Dec 2025 in “NOAA deploys new generation of AI-driven global weather models”
  • Useful for ships and disaster preparation

    “It seems especially useful for cargo ships, with better predictions they could save some fuel and be safer.”

    Comment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

    “30% more time to know exactly where to board up etc. seems very significant”

    Comment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

    “This will be a great layer for our hazard prediction engine.”

    Comment from 8 Sep 2026 in “WeatherNext 3”

What people warn about

Each mark is one comment

  • Vague claims with little methodological detail

    “lack details on how it results in improved accuracy of the forecast”

    Comment from 17 Nov 2025 in “WeatherNext 2: Our most advanced weather forecasting model”

    “a bunch of future-tense words about what could be done by someone, and the requisite hype”

    Comment from 7 Sep 2026 in “WeatherNext 3”

    “it comes off as a magic box”

    Comment from 18 Nov 2025 in “WeatherNext 2: Our most advanced weather forecasting model”
  • Map and viewer hard to read

    “I find it difficult to look at the map and understand the information it relays at the same time.”

    Comment from 7 Sep 2026 in “WeatherNext 3”

    “The online viewer could really, really use Wind Direction as a compass bearing.”

    Comment from 7 Sep 2026 in “WeatherNext 3”

    “the design it's a bit of a letdown - very very very low information density”

    Comment from 8 Sep 2026 in “WeatherNext 3”

What people said

26 of the 27 comments that mention it, newest first. Each links to the original comment.

“Never let a good crisis go to waste for marketing, especially if the product you're promoting is contributing to exacerbating it.”

CriticizesComment from 8 Sep 2026 in “WeatherNext 3”

“the design it's a bit of a letdown - very very very low information density”

CriticizesComment from 8 Sep 2026 in “WeatherNext 3”

“This will be a great layer for our hazard prediction engine.”

RecommendsComment from 8 Sep 2026 in “WeatherNext 3”

“At one point they did release the most accurate weather model by far”

RecommendsComment from 8 Sep 2026 in “WeatherNext 3”

“Init time makes sense to me, it's when the forecast/model is initialized”

MixedComment from 8 Sep 2026 in “WeatherNext 3”

“I find it difficult to look at the map and understand the information it relays at the same time.”

CriticizesComment from 7 Sep 2026 in “WeatherNext 3”

“The online viewer could really, really use Wind Direction as a compass bearing.”

CriticizesComment from 7 Sep 2026 in “WeatherNext 3”

“After signing in I get a 404.”

CriticizesComment from 7 Sep 2026 in “WeatherNext 3”

“None of those words are links or demos. It's just noise.”

CriticizesComment from 7 Sep 2026 in “WeatherNext 3”

“The exploration page is really easy to use.”

RecommendsComment from 7 Sep 2026 in “WeatherNext 3”

“a bunch of future-tense words about what could be done by someone, and the requisite hype”

CriticizesComment from 7 Sep 2026 in “WeatherNext 3”

“the WN3 grid is still quite rough (5km) - but a that's a brutal improvement for many places”

MixedComment from 7 Sep 2026 in “WeatherNext 3”

“It's so cool when an announcement comes with the actual goods.”

RecommendsComment from 3 Sep 2026 in “WeatherNext 3”

“Nothing actually changes on-the-ground for really any consumer of hurricane forecast data anywhere in the world.”

CriticizesComment from 9 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

“they claim to have the same "accuracy" at 3 days that older methods have at 2 days”

CriticizesComment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

“And they are open sourcing it too!!”

RecommendsComment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

“30% more time to know exactly where to board up etc. seems very significant”

RecommendsComment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

“Cool how they integrated both huge machine-scale data and smaller human-curated data for this project.”

RecommendsComment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

“That's way more impactful and interesting than another coding agent”

RecommendsComment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

“It seems especially useful for cargo ships, with better predictions they could save some fuel and be safer.”

RecommendsComment from 8 Aug 2026 in “DeepMind's WeatherNext model achieves breakthrough forecasting cyclones”

“The accuracy of WeatherNext 2 is astounding.”

RecommendsComment from 20 Dec 2025 in “NOAA deploys new generation of AI-driven global weather models”

“I imagine that FGN/WeatherNext 2 would also have similar surprises.”

MixedComment from 20 Dec 2025 in “NOAA deploys new generation of AI-driven global weather models”

“it's generally slower and more memory intensive”

MixedComment from 20 Dec 2025 in “NOAA deploys new generation of AI-driven global weather models”

“it comes off as a magic box”

CriticizesComment from 18 Nov 2025 in “WeatherNext 2: Our most advanced weather forecasting model”

“the new hurricane model was breathtakingly good this season when tested against actual hurricane paths”

RecommendsComment from 17 Nov 2025 in “WeatherNext 2: Our most advanced weather forecasting model”

“lack details on how it results in improved accuracy of the forecast”

MixedComment from 17 Nov 2025 in “WeatherNext 2: Our most advanced weather forecasting model”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.