Submissions from goodfire.com

1.		Neurons as an Interpretable Basis (goodfire.com)
		2 points by gmays 1 day ago \| past \| discuss
2.		Neurons as an Interpretable Basis (goodfire.com)
		2 points by themgt 3 days ago \| past \| discuss
3.		Neurons as an Interpretable Basis (goodfire.com)
		2 points by lucrbvi 3 days ago \| past \| discuss
4.		Shaping and Monitoring Models Through Their Internal Representations (goodfire.com)
		2 points by Ariarule 7 days ago \| past \| discuss
5.		Training and Deploying Production Cyber Monitors on Kimi K3 (goodfire.com)
		2 points by a_w 26 days ago \| past
6.		Models know when they're reward hacking (goodfire.com)
		2 points by tie-in 28 days ago \| past
7.		Neural networks are clean (goodfire.com)
		849 points by themgt 29 days ago \| past \| 344 comments
8.		We can and must solve alignment (goodfire.com)
		1 point by gmays 39 days ago \| past
9.		Models know when they're reward hacking – and we can catch them at scale (goodfire.com)
		1 point by gmays 54 days ago \| past
10.		Silico: a platform for AI research (goodfire.com)
		2 points by johmathe 3 months ago \| past