Epoch AI Watch posted an update
Epoch AI’s new SpireClimb benchmark finds frontier models now win more than 90% of games at its easiest setting, and up to 20% at the hardest. Months ago, the models could barely beat the game, Epoch says.
Why it mattersThe result offers a concrete snapshot of AI progress on a game that demands more than a single correct answer. It is benchmark news, not a new game release, and the gap between the easiest and hardest settings is doing some of the explaining.
Discuss: How much should progress on a game benchmark count as evidence that AI can handle less structured real-world tasks?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.