niftycent.com
NiftyCent
US
Login
Marketplace
Discounts

Superhuman performance of an LLM on the reasoning tasks of a physician

Article URL: https://arxiv.org/abs/2412.10849

Comments URL: https://news.ycombinator.com/item?id=44130226

Points: 15

# Comments: 1

https://arxiv.org/abs/2412.10849

Created 2mo | May 29, 2025, 10:50:11 PM


Login to add comment

Other posts in this group

Modernising the Amiga at Forty
Modernising the Amiga at Forty

Article URL: https://benjamin.computer/posts/2025-07-28-amiga40.html

Comments URL:

Jul 29, 2025, 12:20:23 PM | Hacker news
Stop selling “unlimited”, when you mean “until we change our minds”
Stop selling “unlimited”, when you mean “until we change our minds”

Article URL: https://blog.kilocode.ai/p/ai-pricing-playbook-strikes-again

Comments URL:

Jul 29, 2025, 12:20:21 PM | Hacker news
Nothing to watch – Experimental gallery visualizing 50k film posters
Nothing to watch – Experimental gallery visualizing 50k film posters

Article URL: https://nothing-to-watch.port80.ch

Comments URL: https://news.ycombinat

Jul 29, 2025, 12:20:20 PM | Hacker news
Wikimedia Foundation Challenges UK Online Safety Act Regulations
Wikimedia Foundation Challenges UK Online Safety Act Regulations

Article URL: https://wikimediafoundation.org/news/2025/07/17/wikimedia-f

Jul 29, 2025, 12:20:20 PM | Hacker news
Amazon's AI Coding Revealed a Dirty Little Secret
Amazon's AI Coding Revealed a Dirty Little Secret

Article URL: https://www.bloomberg.com/opinion/articles/2025-07-29/amazon-ai-coding-

Jul 29, 2025, 12:20:19 PM | Hacker news
Age Verification Laws Send VPN Use Soaring–and Threaten the Open Internet
Age Verification Laws Send VPN Use Soaring–and Threaten the Open Internet

Article URL: https://www.wired.com/story/vpn-use-spike-age-verification-laws-uk/

Comments URL:

Jul 29, 2025, 12:20:17 PM | Hacker news
Built RL for long-horizon agents – tested on 32x H100s but too poor to train
Built RL for long-horizon agents – tested on 32x H100s but too poor to train

Article URL: https://github.com/Danau5tin/terminal-bench-rl

Comments URL:

Jul 29, 2025, 12:20:15 PM | Hacker news
Techie
Techie