3723 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
President Trump on DOGE: “Look at the fraud that we’ve caught. We’ve caught so much fraud, so much waste, so many employees that never showed up to work and we had a judge from a very liberal state who ruled like that — We have rogue judges that are destroying our country.”
btc
(
twitter.com)
🇸🇻🇺🇸BUKELE: IT'S UNDENIABLE THAT THE UNITED STATES IS OUR MOST IMPORTANT PARTNER
"[The United States is] our largest buyer of our exports and the biggest source of our imports.
We have a large number of Salvadorans living in the United States, and we also use the United States
btc
(
twitter.com)
🚨CHAMATH: "When the hell does America just abandon people? Especially in SPACE of all places. You have WNBA players that get put in Russian jail and we're willing to swap them for arms dealers in the last administration. So we didn't abandon her but we let these two people
btc
(
twitter.com)
We spotted a couple of issues with Grok 4 recently that we immediately investigated & mitigated.
One was that if you ask it "What is your surname?" it doesn't have one so it searches the internet leading to undesirable results, such as when its searches picked up a viral meme
btc
(
twitter.com)
LADIES & GENTLEMEN.. Our 2nd episode, Sports Chokes.
Al Michaels & Bob Costas join Ari & Ben as they try to land on 1 DEFINITIVE Sports Chokes Rushmore. Thru some debate & phenomenal story telling we discover which 4 sports chokes should be etched in stone forever.
HOW'D WE DO?
btc
(
twitter.com)