Aligning brains into a shared space improves their alignment with LLMs | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Aligning brains into a shared space improves their alignment with LLMs (nature.com)
		5 points by tesserato 5 days ago \| hide \| past \| favorite \| 1 comment

		help

tesserato 5 days ago [–]

Mapping neural activity from multiple individuals into a "shared response space" improves the accuracy of LLM-based brain encoding by 37%.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact