@mister_shroom @jrysana we're against sci fi doomer scenarios depressing ppl / radicalizing them into bombing datacenters. serious safety/alignment researchers who are doing technical work are not the enemy here- we all want AI to do what we want it to do a greater % of the time, that's a capability!
More notes on nearby ideas
Reply · Nov 7, 2023@RokoMijic sighhhh.... see this is where I get frustrated w Safety rhetoric- you want the AI to be aligned to do whatever the human wants them to do…Reply · Mar 4, 2023@RokoMijic @MichaelTrazzi no it's a specific concern that AI xrisk hysteria might trigger some Ted K type of follower into terrorism against AI…Reply · Oct 21, 2022@izzyz @techdominatrix Lol Izzy don’t worry about it, they’ve clearly mixed up AI safety researchers w AI capability engineers (hot)Reply · Feb 19, 2023@JCorvinusVR @skooookum lol yeah, AI safety's worst mistake was using the word "alignment" rather than "non-murderousness"