Submissions from joecarlsmith.com

		Building AIs that do human-like philosophy (joecarlsmith.com)
		1 point by gmays 11 days ago \| past \| discuss
		Building AIs that do human-like philosophy (joecarlsmith.com)
		2 points by freediver 13 days ago \| past \| discuss
		Video and transcript of talk on "Can goodness compete?" (joecarlsmith.com)
		1 point by surprisetalk 6 months ago \| past
		The stakes of AI moral status (joecarlsmith.com)
		3 points by surprisetalk 8 months ago \| past
		Paths and Waystations in AI Safety (joecarlsmith.com)
		1 point by kiyanwang 11 months ago \| past
		Paths and Waystations in AI Safety (joecarlsmith.com)
		1 point by surprisetalk 11 months ago \| past
		Fake thinking and real thinking (joecarlsmith.com)
		88 points by surprisetalk on Jan 30, 2025 \| past \| 18 comments
		Takes on "Alignment Faking in Large Language Models" (joecarlsmith.com)
		11 points by surprisetalk on Dec 19, 2024 \| past \| 13 comments
		Otherness and Control in the Age of AGI (joecarlsmith.com)
		1 point by wjb3 on April 30, 2024 \| past
		On Green (joecarlsmith.com)
		2 points by surprisetalk on April 4, 2024 \| past
		Predictable updating about AI risk (joecarlsmith.com)
		1 point by mjirv on May 14, 2023 \| past
		Predictable updating about AI risk (joecarlsmith.com)
		2 points by kvee on May 10, 2023 \| past