3252 位用户此时在线
- 本站自动实时分享网络热点
- 24小时实时更新
- 所有言论不代表本站态度
- 欢迎对信息踊跃评论评分
- 评分越高，信息越新，排列越靠前
Today we're releasing a developer preview of our next-gen benchmark, ARC-AGI-3.
The goal of this preview, leading up to the full version launch in early 2026, is to collaborate with the community. We invite you to provide feedback to help us build the most robust and effective
btc
(
twitter.com
)
Today we're releasing a developer preview of our next-gen benchmark, ARC-AGI-3.
The goal of this preview, leading up to the full version launch in early 2026, is to collaborate with the community. We invite you to provide feedback to help us build the most robust and effective benchmark possible.
ARC-AGI-3 is the continuation of the ARC series of AI benchmarks:
• Focus on generalization and adaptation to novelty
• Easy for humans, yet extremely difficult for AI
• Built exclusively on Core Knowledge priors, with no other domain-specific knowledge required
The biggest evolution is a complete shift to an interactive format. ARC 3 is a collection of unique, novel games set in the ARC grid world. To succeed, an AI must learn on the fly through efficient trial and error. There are no instructions, so everything is up for you to figure out:
• What are the underlying concepts and mechanics?
• What do the controls do?
• What is the goal, and how do I achieve it?
We are directly probing an AI's ability to efficiently explore, learn, and plan when faced with a completely unknown task. So far, all systems we've tested score 0. Yet all these games are fully solvable by humans in a few minutes with no prior training.
点击图片查看原图
Crazy how we went to the moon and all of a sudden everyone stopped having kids.
It's almost like that singular moment was a huge culture shock - "if we can go to the moon, we can do ANYTHING!!!"
And with the advent of technology, there's so much ANYTHING for us to do that maybe
btc
(
twitter.com)
Something Rep. Al Green told me has really stayed with me:
“I think we have to do as much as we can, as fast as we can to prevent him from becoming a dictator.”
Rep. Green is a man of principle and is genuinely concerned by Trump’s overreach. He should be lauded not punished.
时政
(
twitter.com)
Israël has killed 33,000 babies and children since 2008. So, what’s happening today is no shock to any logical person. 150,000 dead Palestinians since 2008. No one defended them. They broke every law in the book, but no one bats an eye. Sooty to tell you that the survivors today…
时政
(
twitter.com)