Submissions from goodfire.com

1.		Training and Deploying Production Cyber Monitors on Kimi K3 (goodfire.com)
		2 points by a_w 13 days ago \| past \| discuss
2.		Models know when they're reward hacking (goodfire.com)
		2 points by tie-in 14 days ago \| past
3.		Neural networks are clean (goodfire.com)
		849 points by themgt 15 days ago \| past \| 344 comments
4.		We can and must solve alignment (goodfire.com)
		1 point by gmays 25 days ago \| past
5.		Models know when they're reward hacking – and we can catch them at scale (goodfire.com)
		1 point by gmays 40 days ago \| past
6.		Silico: a platform for AI research (goodfire.com)
		2 points by johmathe 87 days ago \| past