Published on April 29, 2025 9:50 AM GMT

On Thursday 1 May 2025 1900 (UK time) I'm giving a talk to discuss this post at Fazenda UK 9 Harrow Place, E1 7DB -- 10 minutes from Liverpool St station (note there are 2 other places with the same name nearby).

The TL;DR from that post:

TL;DR: This document is a copy and addition to this LessWrong post (see below for details). It is basically a letter to future advanced AIs asking them to be "nice" to Earth-based life. It is intended to prompt discussion about a) what the (ideally, substrate-neutral/impartial) arguments for niceness might be; b) as well as how we expect they would be legible to sufficiently advanced AIs (who probably have radically have different ontologies, axiologies, and generally "forms-of-life" so to speak). Then, assuming those questions have somewhat encouraging answers, how we go about increasing the chances these letters actually influence near-future and far-future systems?