x

LESSWRONG
LW

Chad DeChant — LessWrong

Chad DeChant

Chad DeChant

Message

I am a postdoc researcher at New York University working with Marcelo Mattar on safe episodic memory and planning in AI agents.
I received a PhD in Computer Science from Columbia, advised by Daniel Bauer. My dissertation was on enabling robots to remember and report on...

12

1

3mo

Chad DeChant

I am a postdoc researcher at New York University working with Marcelo Mattar on safe episodic memory and planning in AI agents.
I received a PhD in Computer Science from Columbia, advised by Daniel Bauer. My dissertation was on enabling robots to remember and report on...

Episodic memory in AI agents poses new safety risks

I want to draw attention to a set of under-appreciated AI safety risks. These are currently largely theoretical but are very likely to be quite real, quite soon: the risks of developing episodic memory abilities in AI agents. Episodic memory is memory of events we have participated in and is...