Submissions from medium.com/deepmindsafetyresearch

		Alignment of Language Agents (medium.com/deepmindsafetyresearch)
		1 point by dsr12 on March 30, 2021 \| past
		DeepMind: What mechanisms drive agent behaviour? (medium.com/deepmindsafetyresearch)
		3 points by adipandas on March 10, 2021 \| past
		Specification gaming: the flip side of AI ingenuity (medium.com/deepmindsafetyresearch)
		1 point by laurex on May 1, 2020 \| past
		DeepMind Safety Research (medium.com/deepmindsafetyresearch)
		1 point by hongzi on Dec 6, 2019 \| past
		Designing agent incentives to avoid reward tampering (medium.com/deepmindsafetyresearch)
		2 points by hardmaru on Sept 10, 2019 \| past
		DeepMind Safety Blog: Understand Agent Incentives via Causal Influence Diagrams (medium.com/deepmindsafetyresearch)
		3 points by no_identd on April 11, 2019 \| past \| 1 comment
		DeepMind Safety: Designing agent incentives to avoid side effects (medium.com/deepmindsafetyresearch)
		5 points by Jacksonb on March 14, 2019 \| past
		Understanding Agent Incentives with Causal Influence Diagrams (medium.com/deepmindsafetyresearch)
		1 point by stablemap on Feb 27, 2019 \| past
		Scalable agent alignment via reward modeling - DeepMind Safety Research (medium.com/deepmindsafetyresearch)
		16 points by seriousssam on Nov 20, 2018 \| past
		DeepMind Safety Research: Building Safe AI (medium.com/deepmindsafetyresearch)
		2 points by atlasunshrugged on Oct 1, 2018 \| past
		Building safe artificial intelligence: specification, robustness, and assurance (medium.com/deepmindsafetyresearch)
		2 points by lainon on Sept 29, 2018 \| past
		Building safe artificial intelligence: specification, robustness, and assurance (medium.com/deepmindsafetyresearch)
		3 points by seriousssam on Sept 27, 2018 \| past

HN For You